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

    Neuronpedia

    INDEX
    Explanations

    statements expressing feelings or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fou
    -0.83
     Foss
    -0.82
     Niet
    -0.81
     Tid
    -0.76
     TS
    -0.76
     Benz
    -0.74
     plastics
    -0.73
     Bethlehem
    -0.70
     trop
    -0.69
     Camb
    -0.69
    POSITIVE LOGITS
    Ļ
    1.72
    ª
    1.41
    ħ
    1.40
    ı
    1.36
    ĸ
    1.29
    ¬
    1.23
    ¤
    1.20
    Ĩ
    1.19
    Ĵ
    1.17
    į
    1.16
    Act Density 0.258%

    No Known Activations