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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sears
    -0.14
    andre
    -0.14
    ichel
    -0.14
    andom
    -0.14
     Unicorn
    -0.13
    .seed
    -0.13
     Dudley
    -0.13
     among
    -0.13
    AGES
    -0.13
    703
    -0.13
    POSITIVE LOGITS
    ml
    0.15
    rott
    0.15
    defer
    0.15
    تاÙĨ
    0.14
    hest
    0.14
    ffen
    0.14
    atron
    0.14
    lingen
    0.14
    omid
    0.14
     baru
    0.14
    Act Density 0.011%

    No Known Activations