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

    Neuronpedia

    INDEX
    Explanations

    less than symbols followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    кÑĤа
    -0.17
    gue
    -0.16
    ãĥ³ãĥ
    -0.15
    åı¸
    -0.14
    lessness
    -0.14
     ÎĶε
    -0.14
    Å¡ÃŃ
    -0.13
    .comm
    -0.13
    tah
    -0.13
    overy
    -0.13
    POSITIVE LOGITS
    lops
    0.15
    .omg
    0.15
    essional
    0.15
    ocha
    0.14
    ule
    0.14
    isch
    0.14
     Bund
    0.14
    azard
    0.13
    enheim
    0.13
    kip
    0.13
    Act Density 0.045%

    No Known Activations