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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting commands and their associated figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onn
    -0.16
    uss
    -0.14
    owned
    -0.13
    nika
    -0.13
    arga
    -0.13
     Devlet
    -0.13
    reste
    -0.13
    аÑĤÑĮ
    -0.13
     scrim
    -0.13
    arel
    -0.13
    POSITIVE LOGITS
    anitize
    0.15
     opposite
    0.14
    aison
    0.14
    cond
    0.14
    scaled
    0.14
    unga
    0.14
    )(_
    0.14
    rana
    0.14
    luž
    0.14
    ibur
    0.14
    Act Density 0.015%

    No Known Activations