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

    Neuronpedia

    INDEX
    Explanations

    terms related to self-identification and self-reliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herits
    -0.15
    teri
    -0.15
    ele
    -0.15
    pearance
    -0.14
    _UNUSED
    -0.14
    robat
    -0.14
     Dud
    -0.14
    awe
    -0.14
    yne
    -0.14
    \Type
    -0.14
    POSITIVE LOGITS
     taught
    0.19
     proclaimed
    0.19
    iew
    0.18
    pedia
    0.17
    -described
    0.17
    ç«ĭãģ¦
    0.17
    emade
    0.16
     described
    0.16
     tapes
    0.16
    ta
    0.16
    Act Density 0.012%

    No Known Activations