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

    Neuronpedia

    INDEX
    Explanations

    titles of movies and shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affatto
    -0.54
    seamnă
    -0.54
    omiast
    -0.53
    ordinaire
    -0.52
    joso
    -0.50
     desgracia
    -0.50
    WriteBarrier
    -0.49
    IBarButtonItem
    -0.47
    ñores
    -0.47
     plă
    -0.47
    POSITIVE LOGITS
    reportWebVitals
    0.49
     autorytatywna
    0.45
    EDEFAULT
    0.44
     című
    0.42
    WriteTagHelper
    0.40
    Film
    0.40
     Tadeusz
    0.39
    gebra
    0.39
    RatingBar
    0.38
    </i>
    0.38
    Act Density 0.321%

    No Known Activations