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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "leave" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -1.00
    Cordialement
    -0.87
     <<<<<<<<<<<<<<
    -0.82
    Παραπομπές
    -0.77
    BagLayout
    -0.75
    팎
    -0.74
    Amicalement
    -0.73
    ぼちゃ
    -0.72
     Sert
    -0.72
     poppies
    -0.72
    POSITIVE LOGITS
     leave
    2.21
    Leave
    2.10
     Leave
    2.08
    leave
    2.05
     leaving
    1.98
     leaves
    1.97
     LEAVE
    1.93
    LEAVE
    1.85
     Leaving
    1.74
     Leaves
    1.73
    Act Density 0.064%

    No Known Activations