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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating methods or approaches

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tableFuture
    -0.82
    AndEndTag
    -0.81
    ton
    -0.72
     continúas
    -0.72
    νον
    -0.69
     actionTypes
    -0.68
     story
    -0.68
    landen
    -0.66
     तरह
    -0.66
     FileWriter
    -0.65
    POSITIVE LOGITS
     Means
    0.80
    Means
    0.72
     contextLoads
    0.70
    Personendaten
    0.70
     lenker
    0.66
     Niles
    0.62
    epiece
    0.62
     kennis
    0.61
     transférez
    0.61
    ')";
    0.61
    Act Density 0.010%

    No Known Activations