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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utin
    -0.17
    shan
    -0.15
    sv
    -0.15
    ycin
    -0.14
    holm
    -0.14
    uar
    -0.14
    yr
    -0.14
     Kauf
    -0.13
    sys
    -0.13
     Acres
    -0.13
    POSITIVE LOGITS
    /how
    0.30
    -ever
    0.17
    -нибÑĥдÑĮ
    0.17
    /if
    0.17
    -либо
    0.16
    soever
    0.16
    iglia
    0.15
    ок
    0.15
    ëĵł
    0.15
    infeld
    0.14
    Act Density 0.019%

    No Known Activations