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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating caution or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lich
    -0.17
    ÑĤиÑı
    -0.17
    imity
    -0.16
    egov
    -0.15
    oka
    -0.15
    ERCHANT
    -0.14
    ennon
    -0.14
    اÙĩÙħ
    -0.14
    itched
    -0.14
    à¸į
    -0.14
    POSITIVE LOGITS
    iane
    0.17
     Kane
    0.16
     Carpenter
    0.16
    bane
    0.16
    istrovstvÃŃ
    0.15
     Hank
    0.15
    bote
    0.15
     Hew
    0.15
    ATA
    0.14
     Cage
    0.14
    Act Density 0.006%

    No Known Activations