Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 311
    Prev
    Next
    INDEX
    Explanations

    references to repeated concepts or ideas

    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
    undown
    -0.76
    oulos
    -0.74
     misled
    -0.74
     tremend
    -0.74
    itiveness
    -0.72
    itionally
    -0.71
     deceived
    -0.69
     hurry
    -0.69
     destro
    -0.69
    rame
    -0.66
    POSITIVE LOGITS
    ウス
    0.79
    ript
    0.75
    ーン
    0.70
     cries
    0.69
    ries
    0.67
    �
    0.65
    ドラ
    0.63
     Effects
    0.61
     Coff
    0.60
    times
    0.60
    Activations Density 0.255%

    No Known Activations