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

    Neuronpedia

    INDEX
    Explanations

    words related to wearing or donning something on top

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kills
    -0.71
     Reborn
    -0.68
     Daylight
    -0.67
     Bronze
    -0.59
     Amen
    -0.59
     Mellon
    -0.58
     Alma
    -0.57
    UTF
    -0.57
     Abbey
    -0.57
    GMT
    -0.56
    POSITIVE LOGITS
    roying
    0.98
    itored
    0.98
    ility
    0.95
    acters
    0.95
    tenance
    0.92
    alog
    0.89
    orting
    0.88
    aring
    0.88
    ielding
    0.85
    riction
    0.83
    Act Density 0.112%

    No Known Activations