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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "leave" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.78
     <<<<<<<<<<<<<<
    -0.76
    erial
    -0.74
    sikan
    -0.70
     XXIV
    -0.69
    ぼちゃ
    -0.68
    Cordialement
    -0.68
    Παραπομπές
    -0.68
    getInstance
    -0.66
    UTERS
    -0.65
    POSITIVE LOGITS
     leave
    1.97
    Leave
    1.87
     Leave
    1.87
     leaves
    1.83
    leave
    1.83
     leaving
    1.79
     LEAVE
    1.78
     Leaves
    1.72
    LEAVE
    1.70
    leaves
    1.66
    Act Density 0.064%

    No Known Activations