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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of persons or characters along with their roles or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     moot
    -0.75
     Peoples
    -0.64
     unbeliev
    -0.63
     guiActiveUnfocused
    -0.62
    FORE
    -0.62
     Arrow
    -0.62
    ifference
    -0.61
    evidence
    -0.59
    arity
    -0.59
    LESS
    -0.59
    POSITIVE LOGITS
     fluent
    0.71
    aciously
    0.69
    pires
    0.65
    ifa
    0.65
     mastered
    0.64
    otta
    0.63
    )|
    0.63
     surrendered
    0.63
    ?),
    0.62
    ilyn
    0.62
    Act Density 0.671%

    No Known Activations