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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotable phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favor
    -0.76
     bunk
    -0.71
     honor
    -0.71
     nude
    -0.69
     clo
    -0.69
     livestream
    -0.69
     footing
    -0.68
     nested
    -0.67
     encl
    -0.67
     inadequ
    -0.66
    POSITIVE LOGITS
    Therefore
    1.28
    Whereas
    1.27
    It
    1.25
    There
    1.23
    They
    1.22
    If
    1.21
    However
    1.21
    Unless
    1.20
    We
    1.18
    Fortunately
    1.17
    Act Density 0.092%

    No Known Activations