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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and the beginning of quoted speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Saiyan
    -0.78
     shit
    -0.75
     slam
    -0.71
     pee
    -0.71
     bum
    -0.70
     tru
    -0.69
     cul
    -0.69
     veget
    -0.69
     nonexistent
    -0.68
     ranch
    -0.68
    POSITIVE LOGITS
    Our
    1.14
    Unfortunately
    1.12
    Given
    1.12
    However
    1.10
    Based
    1.09
    We
    1.09
    While
    1.09
    These
    1.08
    Although
    1.08
    Therefore
    1.08
    Act Density 0.135%

    No Known Activations