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

    Neuronpedia

    INDEX
    Explanations

    expressions related to profanity and strong language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vider
    -0.16
    orer
    -0.15
    ity
    -0.15
    ÙĪرش
    -0.14
    laden
    -0.14
     Rail
    -0.14
    setter
    -0.13
    icious
    -0.13
     Twin
    -0.13
    ảo
    -0.13
    POSITIVE LOGITS
    .↵↵↵↵↵↵↵↵
    0.15
    ?url
    0.15
    abbage
    0.15
    èĶµ
    0.15
    ardım
    0.14
    adge
    0.14
    ön
    0.14
    .↵↵↵↵↵↵↵↵↵↵
    0.14
    hl
    0.13
    bsd
    0.13
    Act Density 0.012%

    No Known Activations