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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors and expressions of foolishness or stupidity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Abitanti
    -0.39
    StoryboardSegue
    -0.39
     архивлан
    -0.33
     régl
    -0.33
     rapports
    -0.32
    Gruss
    -0.31
    AnchorStyles
    -0.30
     Mela
    -0.30
    cshtml
    -0.29
    documentclass
    -0.29
    POSITIVE LOGITS
    contentLoaded
    0.77
     stupid
    0.69
     fools
    0.69
     Stupid
    0.68
    Stupid
    0.68
    stupid
    0.65
     idiotic
    0.65
    Idiot
    0.63
     foolish
    0.62
     idiot
    0.62
    Act Density 0.246%

    No Known Activations