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

    Neuronpedia

    INDEX
    Explanations

    terms related to capabilities and functional effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дж
    -0.18
    ê
    -0.17
    mers
    -0.16
    lak
    -0.15
    ers
    -0.15
    role
    -0.14
    ANJI
    -0.14
    sdale
    -0.14
    ема
    -0.14
    roller
    -0.14
    POSITIVE LOGITS
    -bodied
    0.21
    /disable
    0.16
    472
    0.16
    acent
    0.15
    (cap
    0.15
    ting
    0.15
    693
    0.15
    uesta
    0.14
    tte
    0.14
    ÐIJÐł
    0.14
    Act Density 0.019%

    No Known Activations