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

    Neuronpedia

    INDEX
    Explanations

    key phrases indicating possession or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     others
    -0.19
     either
    -0.17
    erif
    -0.15
    aggable
    -0.14
    aucoup
    -0.14
    _BITS
    -0.14
     addCriterion
    -0.14
    ategorized
    -0.14
     varying
    -0.13
     EITHER
    -0.13
    POSITIVE LOGITS
     ifndef
    0.15
    ãĤ¹ãĥ¬
    0.15
    |h
    0.14
    æĺŃ
    0.14
    ONE
    0.14
     representations
    0.13
    especially
    0.13
    oba
    0.13
    ikip
    0.13
     ÙħÙĤر
    0.13
    Act Density 0.009%

    No Known Activations