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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial information

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and contextually significant phrases related to statements or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.69
    coat
    -0.66
    ä¸Ĭ
    -0.61
    esh
    -0.61
     flourish
    -0.61
    ãĥį
    -0.60
    Ļ½
    -0.59
    emies
    -0.59
    kees
    -0.59
     perk
    -0.59
    POSITIVE LOGITS
     nor
    1.06
     but
    1.01
    nor
    0.97
    but
    0.96
     Presumably
    0.88
     although
    0.85
     But
    0.85
    perhaps
    0.84
    maybe
    0.84
     specifics
    0.82
    Act Density 0.283%

    No Known Activations