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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or metaphors related to disappointment or critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mapper
    -0.34
     Corre
    -0.32
     Kale
    -0.32
     josh
    -0.31
    ydney
    -0.30
     Calli
    -0.29
    mfenced
    -0.29
     En
    -0.28
     cale
    -0.28
    CASE
    -0.28
    POSITIVE LOGITS
     desmotivaciones
    0.73
    StoryboardSegue
    0.70
    rungsseite
    0.67
    RegressionTest
    0.67
    windowFixed
    0.64
     мәкал
    0.63
     مواليد
    0.60
     resourceCulture
    0.60
    ſehen
    0.60
    yayım
    0.60
    Act Density 0.742%

    No Known Activations