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

    Neuronpedia

    INDEX
    Explanations

    specific verbs and actions related to guidance, direction, and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aign
    -0.16
    KeyPressed
    -0.16
     bees
    -0.15
    iske
    -0.15
     Bars
    -0.15
     Credit
    -0.14
    _finalize
    -0.14
     credit
    -0.14
     def
    -0.14
    ouri
    -0.14
    POSITIVE LOGITS
    ARAM
    0.18
    /stdc
    0.16
    AMY
    0.16
    stav
    0.15
    %A
    0.15
    ustr
    0.15
    verts
    0.14
    ayın
    0.14
    ato
    0.14
    ikat
    0.14
    Act Density 0.001%

    No Known Activations