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

    Neuronpedia

    INDEX
    Explanations

    punctuation related to exclamations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ese
    -0.18
    islav
    -0.18
    ish
    -0.16
    veloper
    -0.15
    esh
    -0.15
    ils
    -0.15
    och
    -0.15
    itz
    -0.14
    iscard
    -0.14
     suite
    -0.14
    POSITIVE LOGITS
    eos
    0.17
    ábado
    0.17
    [](
    0.17
    acob
    0.16
    ÙĬÙĦاد
    0.16
    icense
    0.15
    sgi
    0.15
    Ĥæķ°
    0.15
    shape
    0.15
    gnore
    0.14
    Act Density 0.125%

    No Known Activations