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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and concepts involving defaults and null values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rost
    -0.16
    سÙĩ
    -0.15
    ibar
    -0.15
    usat
    -0.15
    ustos
    -0.14
    illet
    -0.14
     primary
    -0.14
    agt
    -0.14
    ibo
    -0.14
     unre
    -0.14
    POSITIVE LOGITS
     GDK
    0.16
    tor
    0.15
     karÅŁ
    0.14
    orthy
    0.14
    ãĥ³
    0.14
    erville
    0.14
     cigaret
    0.13
    adian
    0.13
    ONUS
    0.13
    uchs
    0.13
    Act Density 0.002%

    No Known Activations