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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    but
    -0.75
     but
    -0.66
    Except
    -0.66
    ablished
    -0.63
     Except
    -0.62
    pecially
    -0.62
     };
    -0.62
    è¦ļéĨĴ
    -0.61
    };
    -0.60
    ;;
    -0.60
    POSITIVE LOGITS
     nonetheless
    1.64
     nevertheless
    1.34
     insists
    1.23
     persists
    1.22
     doesn
    1.19
     isn
    1.19
     hasn
    1.15
     remains
    1.14
     persisted
    1.14
     still
    1.13
    Act Density 0.599%

    No Known Activations