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

    Neuronpedia

    INDEX
    Explanations

    mathematical and logical relationships in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.82
     للمعارف
    -0.72
    
    -0.71
    homonymie
    -0.71
     يتيمه
    -0.71
     estekak
    -0.69
    ########.
    -0.68
     BoxDecoration
    -0.66
     IBOutlet
    -0.65
    UnusedPrivate
    -0.63
    POSITIVE LOGITS
     these
    0.63
    AddHtmlAttribute
    0.59
    सन्दर्भ
    0.57
     THESE
    0.57
    these
    0.56
    These
    0.56
    respectively
    0.53
     queste
    0.50
     These
    0.49
     acestea
    0.48
    Act Density 0.845%

    No Known Activations