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

    Neuronpedia

    INDEX
    Explanations

    characters and symbols, particularly special or non-standard formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phia
    -0.72
    ategory
    -0.65
     âĵĺ
    -0.64
     Tags
    -0.63
    ierre
    -0.63
     [-
    -0.63
    metics
    -0.62
    ¶
    -0.62
    atur
    -0.61
    ffe
    -0.60
    POSITIVE LOGITS
    çĶ°
    1.00
    æĸ¹
    0.88
    代
    0.88
    theless
    0.87
    åij
    0.82
    æĿ
    0.72
    ª
    0.71
    °
    0.69
    ãĥ¯
    0.69
    ä¸
    0.68
    Act Density 0.009%

    No Known Activations