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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctor
    -0.16
    lector
    -0.15
    atto
    -0.14
    elman
    -0.14
    eyer
    -0.14
     Pen
    -0.14
    ساÙĨÛĮ
    -0.14
    ostream
    -0.14
    elf
    -0.14
     Zag
    -0.13
    POSITIVE LOGITS
    EMY
    0.17
    celik
    0.14
     Hayward
    0.14
    _charset
    0.14
    cken
    0.14
    xed
    0.14
    BSD
    0.13
     Verg
    0.13
    ä¾
    0.13
    erten
    0.13
    Act Density 0.291%

    No Known Activations