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

    Neuronpedia

    INDEX
    Explanations

    editor's notes within text

    oai_token-act-pair · gpt-3.5-turbo

    editor's notes and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.71
     scrim
    -0.70
     manif
    -0.68
    uilding
    -0.64
    gur
    -0.63
    NetMessage
    -0.63
    ravel
    -0.63
    structed
    -0.62
    dest
    -0.62
    ardless
    -0.62
    POSITIVE LOGITS
    BOOK
    0.90
    ":"","
    0.88
    :
    0.83
     NOTE
    0.81
     note
    0.78
    :]
    0.76
     EDIT
    0.74
    >:
    0.72
     Keeper
    0.72
     Corrections
    0.69
    Act Density 0.030%

    No Known Activations