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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses that express intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ImageContext
    -1.03
     beginnetje
    -0.89
     ་་
    -0.77
     Balk
    -0.77
    sidemargin
    -0.76
    principalTable
    -0.74
    InitVars
    -0.74
     незавершена
    -0.74
    InjectAttribute
    -0.73
     Efq
    -0.72
    POSITIVE LOGITS
    To
    1.25
     To
    1.21
     Toh
    0.81
     TO
    0.78
    For
    0.74
    to
    0.73
     לד
    0.72
     For
    0.71
    TO
    0.71
     Чтобы
    0.68
    Act Density 0.096%

    No Known Activations