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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to denial

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deny" in the context of rights and equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psc
    -0.73
    rious
    -0.73
    ================================
    -0.72
    rim
    -0.72
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.71
    incinn
    -0.71
    ROM
    -0.71
    =-=-=-=-=-=-=-=-
    -0.71
    enegger
    -0.69
     Announce
    -0.69
    POSITIVE LOGITS
     denial
    0.80
    afe
    0.73
     denies
    0.69
     deny
    0.69
    zzle
    0.69
    ially
    0.67
     outright
    0.67
    ega
    0.66
     denying
    0.65
    elson
    0.64
    Act Density 0.025%

    No Known Activations