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

    Neuronpedia

    INDEX
    Explanations

    character-related terms and analyses in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ew
    -0.18
    igkeit
    -0.18
    eko
    -0.15
    air
    -0.15
    ese
    -0.15
    ey
    -0.15
    otch
    -0.15
    eni
    -0.15
    itzer
    -0.15
    erton
    -0.15
    POSITIVE LOGITS
    istically
    0.22
    isation
    0.19
    ized
    0.18
    izations
    0.18
    nels
    0.17
    ised
    0.17
    untime
    0.15
    nel
    0.15
    ize
    0.15
    ırak
    0.15
    Act Density 0.043%

    No Known Activations