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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the evaluation and description of models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Habit
    -0.16
    _gettime
    -0.14
    شت
    -0.14
     habit
    -0.14
    omo
    -0.13
    stin
    -0.13
     fod
    -0.13
    ober
    -0.13
    ippy
    -0.13
    Lint
    -0.13
    POSITIVE LOGITS
    ctest
    0.14
    avigate
    0.14
    asis
    0.14
    atıcı
    0.13
    atik
    0.13
     trough
    0.13
    arken
    0.13
    anou
    0.13
    alah
    0.13
    mot
    0.13
    Act Density 0.091%

    No Known Activations