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

    Neuronpedia

    INDEX
    Explanations

    discussions about social media platform policies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gedanke
    -0.41
    LabelTagHelper
    -0.41
    RTGC
    -0.39
    mybatisplus
    -0.39
    erequisites
    -0.38
     OnTriggerEnter
    -0.38
     Fernsehen
    -0.38
    DebuggerStep
    -0.38
     suminist
    -0.38
     televisiva
    -0.38
    POSITIVE LOGITS
     users
    0.68
     user
    0.66
     gebruikers
    0.61
     moderation
    0.60
     kullanıcı
    0.58
     engineers
    0.57
     mone
    0.56
     Users
    0.56
     usuários
    0.56
     algorithmic
    0.55
    Act Density 0.425%

    No Known Activations