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

    Neuronpedia

    INDEX
    Explanations

    references to fixed conditions or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.09
     autorytatywna
    -1.05
    PreferredItem
    -0.97
    脚注の使い方
    -0.93
     disambiguazione
    -0.90
     الرياضيه
    -0.87
    aarrggbb
    -0.85
    IsMutable
    -0.84
     المعيارى
    -0.81
    thâu
    -0.79
    POSITIVE LOGITS
     fixed
    0.84
    Fixed
    0.71
     suspended
    0.71
    ess
    0.69
     Fixed
    0.66
    fixed
    0.65
    FIXED
    0.64
    suspended
    0.59
     suspend
    0.57
    ed
    0.55
    Act Density 0.275%

    No Known Activations