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

    Neuronpedia

    INDEX
    Explanations

    punctuation that indicates surprise or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions and expressions of incredulity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emaker
    -0.84
    oreal
    -0.83
    izons
    -0.77
    onds
    -0.73
    20439
    -0.72
    nai
    -0.68
    pkg
    -0.68
    arus
    -0.68
    alyses
    -0.66
    ema
    -0.65
    POSITIVE LOGITS
     Pry
    0.73
     Fantastic
    0.72
     Percy
    0.66
     Anyway
    0.65
     guess
    0.65
    fuck
    0.65
     Hick
    0.64
     Sammy
    0.64
     swear
    0.63
     Pf
    0.63
    Act Density 0.322%

    No Known Activations