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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical data and symbols typically associated with tabular information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rada
    -0.20
    Ñĥки
    -0.16
     disen
    -0.15
    eniz
    -0.15
    973
    -0.14
    amation
    -0.14
    ech
    -0.14
     tane
    -0.14
    tility
    -0.14
    icles
    -0.14
    POSITIVE LOGITS
    oha
    0.16
     Buccane
    0.16
    Pieces
    0.14
    CommandLine
    0.14
    bla
    0.14
    ();++
    0.14
    -cli
    0.14
     Clamp
    0.14
    wat
    0.13
    AGO
    0.13
    Act Density 0.008%

    No Known Activations