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

    Neuronpedia

    INDEX
    Explanations

    words related to physical structures or objects

    oai_token-act-pair · gpt-3.5-turbo

    hyphenated or compound adjectives and nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Expend
    -0.74
     Emirates
    -0.70
     Fiscal
    -0.70
     ND
    -0.68
     unwelcome
    -0.68
     expend
    -0.67
     Icelandic
    -0.67
     latitude
    -0.66
     Monetary
    -0.66
     discretionary
    -0.66
    POSITIVE LOGITS
    shaped
    1.63
    clad
    1.42
    sized
    1.41
    like
    1.39
    covered
    1.35
    filled
    1.32
    laden
    1.30
    haired
    1.30
    based
    1.29
    toe
    1.27
    Act Density 0.092%

    No Known Activations