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

    Neuronpedia

    INDEX
    Explanations

    words or phrases containing special characters like â and Ģ

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and their actions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comprom
    -0.73
     Ambro
    -0.72
     photoc
    -0.67
     horr
    -0.66
     cob
    -0.65
     mathemat
    -0.65
     toget
    -0.64
     ACS
    -0.63
     Sloven
    -0.63
     Marketable
    -0.63
    POSITIVE LOGITS
    Ļ
    1.35
    ¬
    1.23
    ¤
    1.22
    ħ
    1.20
    ĺ
    1.12
    ª
    1.10
    Ħ¢
    1.09
    ı
    1.05
    Ģ
    1.05
    ´
    1.05
    Act Density 0.170%

    No Known Activations