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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ̈́
    -0.90
    #
    -0.90
    RenderAtEndOf
    -0.82
    findpost
    -0.79
    <unused42>
    -0.79
     CreateTagHelper
    -0.79
    <unused41>
    -0.79
    <unused79>
    -0.79
    <pad>
    -0.78
    <unused3>
    -0.78
    POSITIVE LOGITS
    ,
    0.39
     (
    0.36
    w
    0.32
    2
    0.32
    .
    0.31
    -
    0.31
    :
    0.29
    ♩
    0.28
    1
    0.28
    ;
    0.28
    Act Density 0.406%

    No Known Activations