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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and identifiers related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abay
    -0.16
    iggs
    -0.16
    ãĥ³ãĤ¸
    -0.15
    даÑĤ
    -0.15
    cla
    -0.15
    Rare
    -0.14
    VICE
    -0.14
    asic
    -0.14
    bette
    -0.14
     rare
    -0.14
    POSITIVE LOGITS
    μοÏħ
    0.17
    wen
    0.15
    igner
    0.15
    idy
    0.14
    ocator
    0.14
     Kraj
    0.14
    linkplain
    0.13
     Mason
    0.13
     Wand
    0.13
    ammer
    0.13
    Act Density 0.002%

    No Known Activations