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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating adherence to specific standards or guidelines

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     PropTypes
    -0.82
     RISERV
    -0.81
     ARXIV
    -0.81
     smtplib
    -0.79
     Mih
    -0.78
     Namur
    -0.77
    imageio
    -0.74
     Saltar
    -0.74
     GIPHY
    -0.71
     mérit
    -0.71
    POSITIVE LOGITS
     accordance
    1.02
    Véxase
    0.69
     awa
    0.67
    AutoScaleMode
    0.66
     CreateTagHelper
    0.66
    include
    0.65
     تضيفلها
    0.62
    ņš
    0.62
     ComVisible
    0.60
    accord
    0.60
    Act Density 0.004%

    No Known Activations