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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions related to the properties of functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MatDialog
    -0.68
    latego
    -0.67
     QtCore
    -0.65
    DotNetBar
    -0.64
    lgari
    -0.63
     chociaż
    -0.63
     plufieurs
    -0.62
    prefixer
    -0.62
     فريبيس
    -0.61
     Cicero
    -0.60
    POSITIVE LOGITS
    }}^
    0.79
    }^
    0.73
    )^
    0.71
    }_
    0.71
    })^
    0.69
    }}_
    0.65
    )}_
    0.63
    }^\
    0.62
    ))^
    0.62
    ]^
    0.52
    Act Density 1.161%

    No Known Activations