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

    Neuronpedia

    INDEX
    Explanations

    statements or declarations made by individuals, organizations, or authorities

    oai_token-act-pair · gpt-3.5-turbo

    formal communication expressions, particularly statements and legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sake
    -0.73
    pires
    -0.60
     Ajax
    -0.59
    always
    -0.59
    cakes
    -0.58
    ibles
    -0.58
     afar
    -0.56
    hner
    -0.56
    knowledge
    -0.55
    bred
    -0.55
    POSITIVE LOGITS
     outlining
    0.78
     thanking
    0.77
     stating
    0.65
     titled
    0.65
     condem
    0.65
     recommending
    0.64
     indicating
    0.63
     alleging
    0.63
     detailing
    0.63
     wherein
    0.62
    Act Density 0.230%

    No Known Activations