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

    Neuronpedia

    INDEX
    Explanations

    quotations within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overlook
    -0.75
     lookout
    -0.74
     scheduled
    -0.71
     punct
    -0.71
     favor
    -0.69
     moder
    -0.69
     overshadow
    -0.69
     erupt
    -0.68
     slate
    -0.68
     termin
    -0.68
    POSITIVE LOGITS
    We
    1.24
    They
    1.23
    Our
    1.21
    Sometimes
    1.13
    Where
    1.13
    Because
    1.12
    There
    1.11
    It
    1.10
    Russ
    1.09
    I
    1.08
    Act Density 0.083%

    No Known Activations