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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or skepticism about societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aux
    -0.17
    bara
    -0.15
    eval
    -0.14
    æ¿
    -0.14
    ãĥªãĥ¼ãĤº
    -0.14
     Inn
    -0.13
    aight
    -0.13
    angan
    -0.13
    alez
    -0.13
    _callable
    -0.13
    POSITIVE LOGITS
    ç«Ł
    0.20
     anyone
    0.17
     somehow
    0.17
    yte
    0.16
    oui
    0.16
    éra
    0.16
    PERT
    0.15
     à¤ĩतन
    0.15
     STILL
    0.15
    å¦ĤæѤ
    0.15
    Act Density 0.217%

    No Known Activations