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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing disbelief or skepticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of disbelief or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itta
    -0.68
    catentry
    -0.65
    idth
    -0.57
    hift
    -0.57
    WAY
    -0.56
    oway
    -0.56
    arthed
    -0.56
     newcom
    -0.55
    stellar
    -0.54
    ãĤ¢
    -0.54
    POSITIVE LOGITS
    chy
    1.12
    alian
    1.12
     happens
    1.11
     occurs
    1.10
     exists
    1.08
     hurts
    1.08
    's
    1.05
     belongs
    1.03
    unes
    1.02
     wasn
    1.01
    Act Density 0.109%

    No Known Activations