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

    Neuronpedia

    INDEX
    Explanations

    references to programming functions or constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Exists
    -0.15
    unc
    -0.15
    unning
    -0.14
    أس
    -0.14
    isor
    -0.14
    ctest
    -0.13
    ario
    -0.13
    ISA
    -0.13
    arios
    -0.13
    pton
    -0.13
    POSITIVE LOGITS
    eneg
    0.16
    biên
    0.15
    (bind
    0.14
    yas
    0.14
     Lau
    0.14
     âĹĦ
    0.14
    ilden
    0.14
    rowable
    0.13
     Bet
    0.13
    SError
    0.13
    Act Density 0.004%

    No Known Activations