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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names containing "ka"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the token 'ka'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.73
    lessly
    -0.69
    orship
    -0.66
    á½
    -0.64
    aments
    -0.63
    down
    -0.63
    quickShipAvailable
    -0.62
    service
    -0.62
    Ö¼
    -0.60
    downs
    -0.60
    POSITIVE LOGITS
    ichi
    1.11
    osta
    1.03
    iba
    0.95
    esthesia
    0.95
    jac
    0.88
    esthetic
    0.86
    uthor
    0.85
    oru
    0.84
    ja
    0.82
    gee
    0.82
    Act Density 0.009%

    No Known Activations