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

    Neuronpedia

    INDEX
    Explanations

    terms related to cultural or community identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zem
    -0.17
    деÑĢ
    -0.16
    itom
    -0.15
    άλ
    -0.15
    oldt
    -0.15
    žel
    -0.15
    रण
    -0.14
    ìĶĢ
    -0.14
    emain
    -0.14
    },{↵
    -0.14
    POSITIVE LOGITS
     meaning
    0.17
    aset
    0.17
    ans
    0.17
    amos
    0.16
    ki
    0.15
    unes
    0.15
    iero
    0.14
    zs
    0.14
    asts
    0.14
    kk
    0.14
    Act Density 0.225%

    No Known Activations