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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "leave" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagext
    -0.88
    Παραπομπές
    -0.83
    érard
    -0.79
     Sik
    -0.78
    ぼちゃ
    -0.77
    μως
    -0.77
    팎
    -0.74
    Życiorys
    -0.74
    Personensuche
    -0.73
    rungen
    -0.73
    POSITIVE LOGITS
     leaves
    1.76
     Leaves
    1.67
     leave
    1.66
    Leaves
    1.61
    Leave
    1.60
    leaves
    1.59
     LEAVE
    1.58
    leave
    1.57
    LEAVE
    1.55
     Leave
    1.54
    Act Density 0.053%

    No Known Activations