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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements or confirmations, often followed by context or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esson
    -0.17
     although
    -0.16
    ç«Ł
    -0.14
    ylvania
    -0.14
     whats
    -0.14
    emax
    -0.14
    ogn
    -0.13
     either
    -0.13
     vict
    -0.13
    although
    -0.13
    POSITIVE LOGITS
    åķ¦
    0.17
     SOME
    0.17
    igh
    0.16
    æľīäºĽ
    0.16
     конеÑĩно
    0.16
    даÑı
    0.15
    æľīä¸Ģ
    0.15
     occasionally
    0.14
    Some
    0.14
     superf
    0.14
    Act Density 0.056%

    No Known Activations