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

    Neuronpedia

    INDEX
    Explanations

    references to various groups, events, and participation metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seins
    -0.15
    AdapterFactory
    -0.14
    quam
    -0.14
    аÑĩ
    -0.14
    ubb
    -0.13
    olley
    -0.13
    abin
    -0.13
    ãĥ«ãĤ¯
    -0.13
     заÑģÑĤ
    -0.13
    ÑĢаÑĩ
    -0.13
    POSITIVE LOGITS
    å·¦åı³
    0.20
    annes
    0.16
    lou
    0.15
     Hod
    0.14
    okes
    0.14
    zos
    0.14
    onga
    0.14
    asz
    0.14
    setError
    0.13
    .Alpha
    0.13
    Act Density 0.290%

    No Known Activations