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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "cannot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -1.05
    es
    -0.89
    '
    -0.86
    a
    -0.86
    h
    -0.81
     (
    -0.80
    ’
    -0.80
    i
    -0.80
    .
    -0.80
    -
    -0.79
    POSITIVE LOGITS
    ſelves
    1.46
     Anſ
    1.37
     ―――――
    1.35
     ་་
    1.35
     myſelf
    1.33
     doubtnut
    1.28
     muſt
    1.26
     Efq
    1.26
     deſt
    1.26
     Monfieur
    1.25
    Act Density 0.034%

    No Known Activations