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

    Neuronpedia

    INDEX
    Explanations

    political and legislative terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    punctuations, specifically commas, indicating a focus on sentence structure or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oph
    -0.68
    EO
    -0.66
    iph
    -0.65
    ishly
    -0.63
    uci
    -0.62
    ero
    -0.60
    elist
    -0.59
    arily
    -0.59
    atan
    -0.59
    ibo
    -0.58
    POSITIVE LOGITS
     respectively
    0.89
     culminating
    0.80
     Palestin
    0.75
     which
    0.67
     moreover
    0.65
     adherents
    0.64
     namely
    0.63
     coupled
    0.63
    anwhile
    0.62
     analysts
    0.61
    Act Density 0.526%

    No Known Activations