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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 767
    Prev
    Next
    INDEX
    Explanations

    instances of the word "got" and its variations indicating possession or acquisition

    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
    adr
    -0.76
    trust
    -0.73
    puted
    -0.72
    nil
    -0.72
    core
    -0.69
    Counter
    -0.69
    duty
    -0.69
    ellen
    -0.68
    nen
    -0.65
    lander
    -0.65
    POSITIVE LOGITS
    UGE
    0.84
     permission
    0.73
     help
    0.72
     encouragement
    0.68
     embroiled
    0.67
     enthusiastic
    0.66
     blessing
    0.66
    anmar
    0.64
    ILLE
    0.64
     rave
    0.63
    Activations Density 0.070%

    No Known Activations