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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating potential outcomes or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĦãĤĭ
    -0.18
    conde
    -0.17
    azeera
    -0.16
    esi
    -0.15
    eparator
    -0.15
    ctype
    -0.15
    odb
    -0.15
    ————————
    -0.14
    icorn
    -0.14
    ει
    -0.14
    POSITIVE LOGITS
    ily
    0.26
    ness
    0.25
    iness
    0.22
    -have
    0.18
    uous
    0.18
    've
    0.18
    ment
    0.17
    iest
    0.17
    ones
    0.15
    ering
    0.15
    Act Density 0.038%

    No Known Activations