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

    Neuronpedia

    INDEX
    Explanations

    phrases related to competitions or games

    oai_token-act-pair · gpt-3.5-turbo

    negative attributes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.92
    anwhile
    -0.86
    pta
    -0.85
    Ń·
    -0.84
     Reloaded
    -0.74
    uyomi
    -0.73
    ongyang
    -0.73
     Schl
    -0.73
     RTX
    -0.70
    wcs
    -0.69
    POSITIVE LOGITS
    advertising
    1.01
    sized
    0.92
    information
    0.90
    life
    0.89
    lif
    0.86
    arms
    0.85
    sent
    0.83
    susp
    0.83
    purpose
    0.83
    committee
    0.82
    Act Density 0.025%

    No Known Activations