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

    Neuronpedia

    INDEX
    Explanations

    version numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with software versioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accus
    -0.73
     rhy
    -0.67
     allot
    -0.63
    addle
    -0.63
     forgot
    -0.62
    epad
    -0.61
     consuming
    -0.61
     indo
    -0.61
     breathe
    -0.61
     opposing
    -0.61
    POSITIVE LOGITS
    dylib
    1.03
    isSpecialOrderable
    0.82
    ãĥ´ãĤ¡
    0.78
    emetery
    0.77
    xxx
    0.77
    launch
    0.73
    fm
    0.72
    cised
    0.72
    levard
    0.72
    itialized
    0.70
    Act Density 0.078%

    No Known Activations