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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a quality or characteristic of a subject, especially descriptors emphasizing approval or disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.56
    Tikang
    -0.56
     onCreateView
    -0.52
     perfección
    -0.49
     transférez
    -0.48
     inſ
    -0.46
     rhestr
    -0.46
     vectoriales
    -0.46
     juſ
    -0.45
     Majefty
    -0.45
    POSITIVE LOGITS
     lot
    0.59
     bit
    0.46
     few
    0.44
    __*/
    0.43
     a
    0.43
     glimpses
    0.42
     sober
    0.41
    fass
    0.41
     Certain
    0.40
     spitting
    0.40
    Act Density 0.399%

    No Known Activations