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

    Neuronpedia

    INDEX
    Explanations

    phrases related to examples and categories

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "such as" indicating examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     somew
    -0.71
    ĺħ
    -0.62
     exting
    -0.61
     destro
    -0.60
    aution
    -0.59
     withd
    -0.58
     ende
    -0.57
     Accessed
    -0.57
    ccording
    -0.57
    ò
    -0.56
    POSITIVE LOGITS
     as
    1.03
    as
    0.90
    As
    0.70
    asher
    0.69
    ties
    0.67
    asions
    0.64
    asant
    0.63
    iner
    0.61
    amount
    0.60
    ities
    0.59
    Act Density 0.039%

    No Known Activations