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

    Neuronpedia

    INDEX
    Explanations

    special characters that signify formatting or specific inputs in programming and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.19
    asal
    -0.15
    armed
    -0.15
    kuk
    -0.15
    pics
    -0.15
    uft
    -0.14
    arro
    -0.14
    entin
    -0.14
    isel
    -0.14
    asan
    -0.13
    POSITIVE LOGITS
    ctor
    0.15
     tiener
    0.14
     vale
    0.14
    igne
    0.14
    dbo
    0.14
    gm
    0.14
    emat
    0.13
     Jacob
    0.13
    nel
    0.13
    sth
    0.13
    Act Density 0.001%

    No Known Activations