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

    Neuronpedia

    INDEX
    Explanations

    phrases related to moderation and editing in online discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALE
    -0.14
    áš
    -0.14
    lick
    -0.14
    ainty
    -0.14
    _viewer
    -0.14
    bsd
    -0.13
    assen
    -0.13
     app
    -0.13
     layer
    -0.13
    ãĥĹ
    -0.13
    POSITIVE LOGITS
    адж
    0.15
    åİĨ
    0.15
    nell
    0.15
    ì¶ĺ
    0.15
    Ĥ¬
    0.14
    elix
    0.14
    OURS
    0.14
     Closure
    0.14
    WD
    0.14
    oad
    0.14
    Act Density 0.002%

    No Known Activations