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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate potential risks or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.16
    intl
    -0.14
    eming
    -0.14
    572
    -0.14
    маг
    -0.13
    ä½µ
    -0.13
    Ïģιά
    -0.13
    å¥ĩ
    -0.13
    dül
    -0.13
    helm
    -0.13
    POSITIVE LOGITS
    گر
    0.16
    HELL
    0.15
    loff
    0.15
    regor
    0.14
     yat
    0.14
    ENTIAL
    0.13
    èģĺ
    0.13
    mrt
    0.13
     Hell
    0.13
    ngle
    0.13
    Act Density 0.003%

    No Known Activations