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

    Neuronpedia

    INDEX
    Explanations

    references to online communities and their rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.52
    évaluateur
    -0.43
    tvguidetime
    -0.43
    SharedCtor
    -0.41
    原始内容存档于
    -0.41
     Administrativna
    -0.38
    Hozzáférés
    -0.38
    aarrggbb
    -0.37
    Errorf
    -0.36
     😂
    -0.36
    POSITIVE LOGITS
     anon
    0.68
     Anon
    0.61
     Trips
    0.60
    Anon
    0.59
     Kek
    0.58
     kek
    0.58
     faggot
    0.58
    Trips
    0.57
     >>
    0.57
    >>
    0.57
    Act Density 0.277%

    No Known Activations