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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly values and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foreseeable
    -0.70
     outwe
    -0.69
    heads
    -0.67
     wink
    -0.65
     fingerprints
    -0.63
     sails
    -0.62
    onday
    -0.61
     outl
    -0.61
     Izan
    -0.61
     punched
    -0.60
    POSITIVE LOGITS
     ILCS
    0.70
    ©¶æ¥µ
    0.68
    BIL
    0.65
    tro
    0.64
    arb
    0.63
    ccording
    0.62
    imov
    0.62
     Hel
    0.62
    ctory
    0.61
     Meter
    0.61
    Act Density 0.109%

    No Known Activations