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

    Neuronpedia

    INDEX
    Explanations

    contractions of the phrase "do not"

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions and related phrases indicating refusal or non-compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Published
    -0.67
     Unc
    -0.64
     Cance
    -0.63
     newcom
    -0.58
     parting
    -0.57
     distraction
    -0.56
     doomed
    -0.55
     couch
    -0.55
     caster
    -0.55
     nearest
    -0.55
    POSITIVE LOGITS
    't
    1.43
    ned
    0.98
    uts
    0.95
    eness
    0.90
    keys
    0.90
    ÃŃ
    0.90
    gered
    0.87
    itely
    0.87
    acio
    0.86
    its
    0.83
    Act Density 0.104%

    No Known Activations