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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating changes or amendments in policies or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rop
    -0.16
    ilet
    -0.14
    íĸ¥
    -0.14
     new
    -0.13
    çĶ²
    -0.13
    ugin
    -0.13
    ument
    -0.13
    _extensions
    -0.13
    ÏĦεÏģ
    -0.13
    issing
    -0.12
    POSITIVE LOGITS
    ếp
    0.17
    existing
    0.17
     existing
    0.17
    ascus
    0.15
    estruct
    0.15
    abez
    0.15
    ritos
    0.15
    าหล
    0.14
    acceptable
    0.14
     originally
    0.14
    Act Density 0.145%

    No Known Activations