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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "begin" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nosaurus
    -0.62
     Turquía
    -0.56
    lottes
    -0.55
    Forrest
    -0.51
    urismo
    -0.50
     Suiza
    -0.50
    wiſe
    -0.49
    Porto
    -0.49
    tská
    -0.49
    lt
    -0.48
    POSITIVE LOGITS
     Begin
    1.05
    Begin
    0.98
     begin
    0.98
     begins
    0.90
     BEGIN
    0.84
     Begins
    0.84
    begins
    0.84
     Beginning
    0.81
     beginning
    0.77
     BEGINNING
    0.74
    Act Density 0.111%

    No Known Activations