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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĽnie
    -0.17
    405
    -0.16
     Kits
    -0.15
    raÄį
    -0.14
    iba
    -0.14
    ust
    -0.14
    ault
    -0.14
    ;set
    -0.13
    илÑĮ
    -0.13
    aucoup
    -0.13
    POSITIVE LOGITS
    abar
    0.15
    adt
    0.15
    ardon
    0.15
    mur
    0.15
     existential
    0.15
    uno
    0.15
    illis
    0.15
    actic
    0.14
    ayne
    0.14
     wor
    0.14
    Act Density 0.052%

    No Known Activations