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

    Neuronpedia

    INDEX
    Explanations

    text related to government actions or events in the news

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irection
    -0.68
    oph
    -0.67
    EO
    -0.65
    MpServer
    -0.63
    ero
    -0.62
    LV
    -0.62
    ibo
    -0.61
     aut
    -0.61
    rage
    -0.61
    minster
    -0.60
    POSITIVE LOGITS
     respectively
    0.91
    perty
    0.79
     moreover
    0.76
     meanwhile
    0.76
     namely
    0.75
     culminating
    0.71
    anwhile
    0.71
     however
    0.69
    }"
    0.68
     convol
    0.68
    Act Density 0.785%

    No Known Activations