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

    Neuronpedia

    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scheduled
    -0.74
     complement
    -0.73
     seasoned
    -0.72
     comple
    -0.71
     packed
    -0.70
     refinery
    -0.70
    bered
    -0.70
     reconcil
    -0.69
     arch
    -0.69
     enrol
    -0.69
    POSITIVE LOGITS
    Hey
    1.34
    Dear
    1.30
    We
    1.28
    Our
    1.25
    Hi
    1.23
    Hello
    1.23
    What
    1.20
    Everything
    1.19
    Every
    1.18
    I
    1.17
    Act Density 0.115%

    No Known Activations