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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "leave"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disponibilités
    -0.62
    tôi
    -0.59
    Παραπομπές
    -0.58
    ufort
    -0.58
    ところで
    -0.58
    erial
    -0.57
    исправ
    -0.56
     Pingback
    -0.56
     uintptr
    -0.55
    abadi
    -0.55
    POSITIVE LOGITS
     leave
    3.56
     Leave
    3.41
    Leave
    3.41
    leave
    3.40
     LEAVE
    3.17
     leaving
    2.88
    LEAVE
    2.83
     Leaving
    2.65
    leaving
    2.64
     leaves
    2.62
    Act Density 0.074%

    No Known Activations