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

    Neuronpedia

    INDEX
    Explanations

    references to news articles or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eh
    -0.17
    erties
    -0.16
    thon
    -0.16
    ubat
    -0.16
    bert
    -0.15
    ingham
    -0.15
    icer
    -0.15
     ber
    -0.14
     eh
    -0.14
    elow
    -0.14
    POSITIVE LOGITS
    ÏĪε
    0.15
    ][_
    0.15
    ought
    0.14
    amber
    0.14
    åĭĻ
    0.14
    ambre
    0.14
    /licenses
    0.14
    icas
    0.14
    خاÙĨÙĩ
    0.14
    chwitz
    0.14
    Act Density 0.002%

    No Known Activations