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

    Neuronpedia

    INDEX
    Explanations

    percentage values and references to threshold settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.69
    帖最后由
    -0.68
    AndEndTag
    -0.65
    "));
    -0.64
    دانشنامهٔ
    -0.63
    EntityFramework
    -0.59
    "]);
    -0.58
    IntoConstraints
    -0.56
    )]
    -0.55
     ?>
    -0.55
    POSITIVE LOGITS
    Returns
    0.91
     Returns
    0.91
     RETURNS
    0.86
     returns
    0.85
     Arguments
    0.80
    Parameters
    0.79
    returns
    0.76
    RETURNS
    0.73
    Args
    0.73
     Parameters
    0.73
    Act Density 0.513%

    No Known Activations