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

    Neuronpedia

    INDEX
    Explanations

    quantitative metrics or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lenker
    -0.83
     kasarigan
    -0.81
    NameInMap
    -0.81
    Kanpo
    -0.73
    èdia
    -0.69
    Искәрмәләр
    -0.69
    AndEndTag
    -0.68
    exels
    -0.68
     الحره
    -0.67
    djangoproject
    -0.66
    POSITIVE LOGITS
    得
    0.46
    httphttps
    0.46
    ⓘ
    0.44
     Ho
    0.44
    χρι
    0.42
    توض
    0.42
    _(
    0.41
     Sob
    0.41
    roba
    0.40
    ricing
    0.38
    Act Density 0.625%

    No Known Activations