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

    Neuronpedia

    INDEX
    Explanations

    information related to discussions, analyses, and comparisons between different topics or subjects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     madonna
    -0.68
     curé
    -0.57
     lovel
    -0.52
     beaute
    -0.51
     javier
    -0.50
     ardour
    -0.50
     chivalry
    -0.49
     accla
    -0.48
     parlement
    -0.48
     ?...
    -0.48
    POSITIVE LOGITS
     ourselves
    0.70
    GEBURTSDATUM
    0.67
     tayo
    0.62
    OGND
    0.58
     pylab
    0.57
    centralwidget
    0.54
     tanong
    0.53
     natin
    0.53
    onOptions
    0.50
     poważ
    0.50
    Act Density 0.301%

    No Known Activations