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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that resemble code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apro
    -0.15
    aney
    -0.15
    .jetbrains
    -0.14
    umann
    -0.14
    afil
    -0.13
    ild
    -0.13
    owie
    -0.13
     Ze
    -0.13
     L
    -0.12
    redd
    -0.12
    POSITIVE LOGITS
    nton
    0.20
    ommen
    0.15
    allis
    0.14
    ãĥ©ãĤ¤ãĥ³
    0.14
    ’ta
    0.14
    oldur
    0.14
    å²³
    0.13
    esda
    0.13
    312
    0.13
    thouse
    0.13
    Act Density 0.006%

    No Known Activations