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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical sensations and bodily reactions

    oai_token-act-pair · gpt-3.5-turbo

    variations of word endings primarily associated with humor or colloquial language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scant
    -0.73
     lieu
    -0.72
    ICAN
    -0.72
    ĪĴ
    -0.72
     inaction
    -0.71
     triangle
    -0.69
     dyn
    -0.67
     absence
    -0.66
     Dia
    -0.66
     disparate
    -0.65
    POSITIVE LOGITS
    glers
    0.89
    oslav
    0.87
    bart
    0.75
    puff
    0.74
    azines
    0.73
    finder
    0.71
    onyms
    0.70
    bilt
    0.70
    bite
    0.70
    admin
    0.70
    Act Density 0.062%

    No Known Activations