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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pix
    -0.15
    arto
    -0.15
    oice
    -0.15
    infeld
    -0.15
    alice
    -0.15
    colo
    -0.15
    lamaz
    -0.14
    UPPORT
    -0.14
    prefs
    -0.14
    VV
    -0.14
    POSITIVE LOGITS
    μÏĮ
    0.16
    æĭ³
    0.14
    533
    0.14
    ervas
    0.14
    kaar
    0.14
    *"
    0.14
    ायल
    0.13
     organisers
    0.13
    å¸
    0.13
     bil
    0.13
    Act Density 0.171%

    No Known Activations