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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting decision-making or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chet
    -0.16
    ekl
    -0.15
    пÑĤом
    -0.15
    -fontawesome
    -0.14
    leston
    -0.14
    uchi
    -0.14
    aug
    -0.14
    astreet
    -0.14
    лей
    -0.14
    antas
    -0.14
    POSITIVE LOGITS
     Wing
    0.17
    ero
    0.15
    illas
    0.15
    -wing
    0.15
     wing
    0.15
    ainer
    0.15
    erno
    0.15
    اعت
    0.15
    ér
    0.14
     lean
    0.14
    Act Density 0.107%

    No Known Activations