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

    Neuronpedia

    INDEX
    Explanations

    words related to the initiation or beginning of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CopyWith
    -0.71
     שוליים
    -0.61
    Билгалдахарш
    -0.55
    -};
    -0.55
    FieldBuilder
    -0.53
    Viitteet
    -0.53
    AutoScaleMode
    -0.53
    wości
    -0.53
    پیوند
    -0.53
    הערות
    -0.52
    POSITIVE LOGITS
     start
    2.58
     starts
    2.39
     Start
    2.35
     Starts
    2.27
     begin
    2.24
    Start
    2.23
    start
    2.20
     beginning
    2.14
     starting
    2.13
     START
    2.13
    Act Density 0.287%

    No Known Activations