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

    Neuronpedia

    INDEX
    Explanations

    the letter 'i' and its various forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jÃŃm
    -0.15
    ans
    -0.15
    eva
    -0.15
    rone
    -0.14
    jos
    -0.14
    jest
    -0.14
    jet
    -0.14
    jug
    -0.14
    ole
    -0.14
    ehr
    -0.14
    POSITIVE LOGITS
    ing
    0.18
    lust
    0.17
    neck
    0.17
    Ïģο
    0.16
    s
    0.16
    most
    0.16
    cott
    0.16
    work
    0.16
    ary
    0.16
    ÏĦÏģο
    0.15
    Act Density 0.061%

    No Known Activations