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

    Neuronpedia

    INDEX
    Explanations

    numbers and mathematical probabilities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.99
    ArgsConstructor
    -0.88
     forKey
    -0.87
     &___
    -0.84
    migrationBuilder
    -0.83
    httphttps
    -0.83
    -0.81
     estekak
    -0.79
     كومونز
    -0.79
    ftagPool
    -0.79
    POSITIVE LOGITS
    ↵↵
    0.73
    <eos>
    0.68
    ↵
    0.49
    ↵↵↵
    0.48
    htm
    0.40
     Phillips
    0.39
    .
    0.39
     decorar
    0.38
     энциклопедия
    0.38
     aras
    0.37
    Act Density 0.006%

    No Known Activations