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

    Neuronpedia

    INDEX
    Explanations

    references to celebrity names and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </tfoot>
    -0.56
     AssemblyCulture
    -0.52
     nawr
    -0.51
     MessageBoxIcon
    -0.51
    Cambios
    -0.51
    stdafx
    -0.51
    mentaires
    -0.50
    othelioma
    -0.49
    lillah
    -0.49
    itinéraire
    -0.48
    POSITIVE LOGITS
     Reese
    0.72
     Roskov
    0.70
     Halle
    0.67
     Lup
    0.66
     Zend
    0.66
     Miley
    0.66
     Demi
    0.64
    Bey
    0.64
    Halle
    0.63
    Reese
    0.63
    Act Density 0.207%

    No Known Activations