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

    Neuronpedia

    INDEX
    Explanations

    terms expressing a negative evaluation or judgment towards actions or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.78
    LayoutStyle
    -0.70
    Accurate
    -0.67
     Accurate
    -0.66
     ""],
    -0.62
    Приятного
    -0.62
    AutoScale
    -0.61
     lenker
    -0.61
    Euer
    -0.59
    XmlAccessorType
    -0.59
    POSITIVE LOGITS
     silly
    1.04
     stupid
    0.89
    silly
    0.89
     dumb
    0.88
     ridiculous
    0.83
    dumb
    0.79
    stupid
    0.75
     absurd
    0.75
     stupidly
    0.73
     embarrass
    0.72
    Act Density 0.086%

    No Known Activations