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

    Neuronpedia

    INDEX
    Explanations

    percentages and associated statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deniz
    -0.16
    oria
    -0.15
    rint
    -0.14
    ãĥ¬ãĥ³
    -0.13
     Attention
    -0.13
    berman
    -0.13
    sko
    -0.13
     exclusive
    -0.13
     Wagner
    -0.13
    atham
    -0.13
    POSITIVE LOGITS
    ayet
    0.16
    outu
    0.15
    aci
    0.15
    Opens
    0.14
    ör
    0.14
    leigh
    0.14
    rát
    0.14
    ammers
    0.14
    ewidth
    0.14
    ru
    0.14
    Act Density 0.001%

    No Known Activations