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

    Neuronpedia

    INDEX
    Explanations

    instances of contemptuous behavior or situations depicting contempt

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contempt" and related terms reflecting disapproval or disdain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hemor
    -0.70
     encyclopedia
    -0.70
    ramid
    -0.66
     toget
    -0.64
     Lans
    -0.64
     livest
    -0.64
     scen
    -0.64
    akeru
    -0.63
     misunder
    -0.63
     opio
    -0.62
    POSITIVE LOGITS
    uously
    1.45
    uous
    1.38
    fully
    1.19
    ful
    1.06
    ible
    0.93
    ibly
    0.91
    uality
    0.88
    urous
    0.88
    acy
    0.86
    ateurs
    0.85
    Act Density 0.036%

    No Known Activations