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

    Neuronpedia

    INDEX
    Explanations

    references to numbers and quantities

    oai_token-act-pair · gpt-3.5-turbo

    repeated punctuation or commas in a text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jad
    -0.68
    itionally
    -0.67
    obin
    -0.62
    orer
    -0.61
    ites
    -0.61
    NK
    -0.60
    rage
    -0.58
    vers
    -0.58
    ument
    -0.56
    allo
    -0.56
    POSITIVE LOGITS
    76561
    0.80
    FontSize
    0.71
     etc
    0.71
     diminishing
    0.64
     albeit
    0.63
    ModLoader
    0.63
    ilation
    0.62
     illum
    0.61
     Euph
    0.61
     namely
    0.60
    Act Density 0.824%

    No Known Activations