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

    Neuronpedia

    INDEX
    Explanations

    references to accountability and obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENCIL
    -0.16
    clud
    -0.15
    iner
    -0.15
     erken
    -0.15
    lobal
    -0.15
    ÙIJب
    -0.15
    her
    -0.15
    ider
    -0.13
    igi
    -0.13
    èĬ
    -0.13
    POSITIVE LOGITS
    feit
    0.16
    asil
    0.16
    finger
    0.15
    chia
    0.15
    auen
    0.14
    erable
    0.14
    Culture
    0.14
    ازد
    0.14
    eon
    0.14
    496
    0.14
    Act Density 0.010%

    No Known Activations