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

    Neuronpedia

    INDEX
    Explanations

    references to careers or professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENARIO
    -0.15
    zych
    -0.14
     Stark
    -0.14
    enstein
    -0.14
    ibold
    -0.13
     Crest
    -0.13
    klä
    -0.13
     glands
    -0.13
     Loud
    -0.13
    olest
    -0.13
    POSITIVE LOGITS
    ÄĽÅ¾
    0.19
    ort
    0.17
    berman
    0.17
     ActionTypes
    0.15
    441
    0.15
    ikki
    0.15
    zig
    0.15
    343
    0.14
    conti
    0.14
     Bucc
    0.14
    Act Density 0.033%

    No Known Activations