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

    Neuronpedia

    INDEX
    Explanations

    terms related to condemnation or strong criticism

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ―――――
    -1.01
     myſelf
    -0.94
     itſelf
    -0.92
     Theſe
    -0.90
     iſt
    -0.86
     themſelves
    -0.82
    TagMode
    -0.82
     Reſ
    -0.81
     ſeveral
    -0.80
     ſmall
    -0.79
    POSITIVE LOGITS
    !
    0.51
     now
    0.49
     cherchés
    0.48
    webElementXpaths
    0.48
    <eos>
    0.47
    A
    0.47
     A
    0.47
     it
    0.46
    jstor
    0.46
     MainAxisSize
    0.46
    Act Density 0.243%

    No Known Activations