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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to ethnic or cultural backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.91
    HCR
    -0.89
     Parables
    -0.88
    PsyNetMessage
    -0.76
    Ö¼
    -0.75
    tumblr
    -0.74
    gur
    -0.74
    etsk
    -0.72
    rera
    -0.71
    çīĪ
    -0.71
    POSITIVE LOGITS
     Anglo
    1.07
    ixture
    0.70
    ctions
    0.70
     Druid
    0.70
     Jew
    0.68
    entimes
    0.67
    minster
    0.66
     vigilant
    0.65
     Sax
    0.64
     supremacist
    0.64
    Act Density 0.003%

    No Known Activations