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

    Neuronpedia

    INDEX
    Explanations

    words related to societal or systemic issues and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.59
     Akad
    -0.53
    gerald
    -0.52
    reactivex
    -0.51
     ufe
    -0.50
     courage
    -0.50
     cowardly
    -0.49
     impul
    -0.49
     inside
    -0.49
    soka
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.93
    TagMode
    0.83
     contextLoads
    0.69
    setVerticalGroup
    0.69
    findpost
    0.69
     autorytatywna
    0.69
     мәкалә
    0.69
    AddHtmlAttribute
    0.68
     noDo
    0.67
     szóci
    0.66
    Act Density 1.401%

    No Known Activations