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

    Neuronpedia

    INDEX
    Explanations

    comments or comments-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to comments and commentary in online discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lay
    -0.75
    icz
    -0.73
     Sinai
    -0.69
     Metatron
    -0.68
     Lansing
    -0.67
    red
    -0.65
    nown
    -0.64
    borne
    -0.64
     Lans
    -0.63
    ulic
    -0.62
    POSITIVE LOGITS
    ariat
    0.98
    aries
    0.93
    ators
    0.91
    ature
    0.89
    arial
    0.79
    edin
    0.79
     threads
    0.78
    oras
    0.77
     sections
    0.77
    aires
    0.77
    Act Density 0.059%

    No Known Activations