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

    Neuronpedia

    INDEX
    Explanations

    words related to exemplary representation or embodiment of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wick
    -0.16
    aram
    -0.16
     even
    -0.15
    ĥ
    -0.15
     Cu
    -0.14
     cu
    -0.14
     favourite
    -0.14
     dual
    -0.14
     Pant
    -0.14
    andr
    -0.14
    POSITIVE LOGITS
    jed
    0.15
    weis
    0.14
    empo
    0.14
    IZED
    0.14
    ATRIX
    0.14
    atrix
    0.14
    urable
    0.14
    odon
    0.14
    å¸
    0.13
    NING
    0.13
    Act Density 0.016%

    No Known Activations