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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apparaat
    -0.70
     gewicht
    -0.69
     handen
    -0.68
     wikipagina
    -0.66
     mijne
    -0.65
     gevaar
    -0.64
     voegen
    -0.64
    ViewFeatures
    -0.64
     risico
    -0.63
     moeite
    -0.63
    POSITIVE LOGITS
    abestanden
    0.95
     يتيمه
    0.63
    Linq
    0.61
     Bakker
    0.61
    Geplaatst
    0.60
     programme
    0.57
    adpleegd
    0.56
    OPSIS
    0.55
    ernalia
    0.54
    Portail
    0.54
    Act Density 0.256%

    No Known Activations