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

    Neuronpedia

    INDEX
    Explanations

    words related to the verification and validation of models or systems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bague
    -0.86
     charité
    -0.77
    aarrggbb
    -0.76
     asciug
    -0.73
    WidgetItem
    -0.73
     pitié
    -0.70
     boisson
    -0.69
    ValueStyle
    -0.68
     amitié
    -0.68
    byr
    -0.68
    POSITIVE LOGITS
    }}/>
    0.75
     يتيمه
    0.72
    ))/(
    0.71
     Ziegler
    0.68
    ()])
    0.67
    ]")
    0.67
    ")->
    0.66
    )")
    0.66
    "=>$
    0.65
    erokee
    0.65
    Act Density 0.008%

    No Known Activations