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

    Neuronpedia

    INDEX
    Explanations

    quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shit
    -0.91
     crap
    -0.85
     guy
    -0.79
     stuff
    -0.79
     bean
    -0.77
     asshole
    -0.76
     creep
    -0.74
     shake
    -0.73
     gonna
    -0.73
     jug
    -0.72
    POSITIVE LOGITS
    Our
    1.47
    Such
    1.44
    While
    1.43
    Although
    1.42
    Therefore
    1.39
    These
    1.38
    Despite
    1.38
    Given
    1.37
    We
    1.37
    However
    1.36
    Act Density 0.142%

    No Known Activations