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

    Neuronpedia

    INDEX
    Explanations

    references to dialogues or quotes in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     taxpayer
    -0.15
     Armen
    -0.15
    oly
    -0.15
    Cho
    -0.15
     magn
    -0.15
    678
    -0.14
    emento
    -0.14
     Juda
    -0.14
     wiki
    -0.14
    ully
    -0.14
    POSITIVE LOGITS
    caret
    0.15
    é£Ľ
    0.15
    QUIRE
    0.14
    uard
    0.14
    ænd
    0.14
    PEAR
    0.14
    åĭ
    0.14
    omer
    0.14
    rats
    0.14
     chatte
    0.14
    Act Density 0.025%

    No Known Activations