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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     “
    -0.81
     "
    -0.77
     ”
    -0.73
     ",
    -0.67
    aarrggbb
    -0.65
    ***********/
    -0.64
     ").
    -0.64
    //
    -0.63
    ]').
    -0.63
     "..\..\..\
    -0.62
    POSITIVE LOGITS
     ſeveral
    0.90
     Cæsar
    0.86
     Shakspeare
    0.86
     Diſ
    0.83
     Anfitrión
    0.83
    Viitteet
    0.81
     Efq
    0.81
     pleaſure
    0.81
     whoſe
    0.80
     Reſ
    0.80
    Act Density 0.032%

    No Known Activations