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

    Neuronpedia

    INDEX
    Explanations

    references to software versions

    oai_token-act-pair · gpt-3.5-turbo

    references to software version numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.85
    redo
    -0.84
    usters
    -0.77
    ulhu
    -0.77
    agher
    -0.76
    isse
    -0.74
    rontal
    -0.73
    taboola
    -0.73
    seek
    -0.70
    rib
    -0.70
    POSITIVE LOGITS
     version
    0.94
     versions
    0.90
    added
    0.87
    Versions
    0.87
     VERS
    0.86
    UID
    0.84
     thereof
    0.82
     mismatch
    0.80
     Version
    0.78
     incompatible
    0.77
    Act Density 0.020%

    No Known Activations