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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical variations or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astle
    -0.15
    yme
    -0.14
    AF
    -0.14
     McLaren
    -0.14
     Chapman
    -0.14
    istung
    -0.14
     Forward
    -0.13
     Operand
    -0.13
     Marketable
    -0.13
    luv
    -0.13
    POSITIVE LOGITS
    ött
    0.16
    LOSS
    0.16
    237
    0.15
     æ¸
    0.15
     across
    0.15
     from
    0.14
    errat
    0.14
     mate
    0.14
    anes
    0.14
     throughout
    0.14
    Act Density 0.021%

    No Known Activations