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

    Neuronpedia

    INDEX
    Explanations

    references to political entities or controversial historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     silence
    -0.63
    bernatorial
    -0.63
    gements
    -0.63
    ezvous
    -0.62
    gment
    -0.62
    gments
    -0.62
    verage
    -0.61
     formats
    -0.61
    eanor
    -0.60
    uality
    -0.60
    POSITIVE LOGITS
     onwards
    0.73
     Ended
    0.62
     Logged
    0.61
    ateurs
    0.60
     contractor
    0.59
     =================================================================
    0.58
    iets
    0.57
    anmar
    0.57
    edes
    0.56
    senal
    0.55
    Act Density 0.661%

    No Known Activations