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

    Neuronpedia

    INDEX
    Explanations

    references to specific measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kami
    -0.17
     Cup
    -0.16
    orias
    -0.14
    814
    -0.14
    ãĥ´ãĤ£
    -0.14
    agher
    -0.14
    DataReader
    -0.14
    ajaran
    -0.14
     crosses
    -0.14
    749
    -0.14
    POSITIVE LOGITS
     Barth
    0.17
     atoms
    0.16
    коÑĢ
    0.16
    jen
    0.15
    RelativeTo
    0.15
    atoms
    0.15
    mps
    0.14
    _ff
    0.14
    »
    0.14
     inds
    0.14
    Act Density 0.002%

    No Known Activations