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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    parts of speech related to proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cort
    -0.76
     contrace
    -0.71
    atari
    -0.68
    ģĸ
    -0.67
     subp
    -0.66
     taxp
    -0.64
     dock
    -0.64
     thriving
    -0.64
     pods
    -0.63
    SpaceEngineers
    -0.63
    POSITIVE LOGITS
    hof
    0.78
    sonian
    0.74
    wer
    0.73
    schild
    0.73
    acci
    0.69
    iors
    0.67
    kas
    0.67
    culosis
    0.67
    aux
    0.65
    Roberts
    0.65
    Act Density 0.199%

    No Known Activations