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

    Neuronpedia

    INDEX
    Explanations

    phrases related to denial or refusal of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.88
    BAT
    -0.75
    rious
    -0.73
    Ec
    -0.71
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.70
    ateg
    -0.69
    ONEY
    -0.69
    psc
    -0.69
    oiler
    -0.68
    =-=-=-=-
    -0.68
    POSITIVE LOGITS
    afe
    0.74
     denial
    0.73
     prejudice
    0.70
     outright
    0.68
     access
    0.67
    ļéĨĴ
    0.65
    ega
    0.64
     gratification
    0.64
     parole
    0.64
    ially
    0.63
    Act Density 0.032%

    No Known Activations