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

    Neuronpedia

    INDEX
    Explanations

    different types of document formatting and layout elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.81
    ç¥ŀ
    -0.79
    stals
    -0.73
    ozo
    -0.69
    ãĥŃ
    -0.65
    inyl
    -0.65
    ĪĴ
    -0.63
    uously
    -0.63
    ãĥ¼ãĥĨ
    -0.62
    ãĥŀ
    -0.61
    POSITIVE LOGITS
    vous
    0.78
    ree
    0.74
    08
    0.71
    1080
    0.69
    07
    0.69
    REE
    0.68
    05
    0.65
    01
    0.65
    tails
    0.64
    09
    0.64
    Act Density 0.167%

    No Known Activations