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

    Neuronpedia

    INDEX
    Explanations

    words related to sudden or rapid events or changes

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with causes and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erness
    -0.73
     Wing
    -0.68
     Worldwide
    -0.68
     vigorously
    -0.65
     RSA
    -0.63
    Ĥ¬
    -0.62
     Nationwide
    -0.60
     tailored
    -0.60
     enthusiastically
    -0.60
     audition
    -0.60
    POSITIVE LOGITS
    itous
    1.57
    itates
    1.32
    itating
    1.30
    itated
    1.30
    itate
    1.25
    ice
    1.12
    itant
    1.09
    isions
    1.08
    itial
    1.00
    ices
    0.99
    Act Density 0.047%

    No Known Activations