© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1153
    Prev
    Next
    INDEX
    Explanations

    the word "when" in relation to significant events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izons
    -0.73
    issance
    -0.72
    yssey
    -0.68
    ldom
    -0.61
    pty
    -0.59
     ridden
    -0.59
     Nanto
    -0.57
    ét
    -0.57
     Pinball
    -0.56
     embarked
    -0.56
    POSITIVE LOGITS
     administrators
    0.65
     ingred
    0.65
    ridge
    0.61
     editors
    0.61
     reporters
    0.60
    ions
    0.60
    STON
    0.59
     inspectors
    0.59
     officials
    0.58
     investigators
    0.58
    Activations Density 0.055%

    No Known Activations