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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases indicating positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plode
    -0.15
    ollo
    -0.15
     Vys
    -0.14
    ätz
    -0.14
    IDA
    -0.14
     Tits
    -0.14
    getSingleton
    -0.14
    lech
    -0.14
    SendMessage
    -0.14
    068
    -0.13
    POSITIVE LOGITS
     stint
    0.18
     role
    0.17
     dual
    0.17
     scholarship
    0.16
     streak
    0.16
     series
    0.15
    èĹı
    0.15
     personal
    0.15
     seat
    0.15
     suite
    0.15
    Act Density 0.158%

    No Known Activations