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

    Neuronpedia

    INDEX
    Explanations

    detailed documentation or metadata related to software components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.71
     Bene
    -0.69
    Pare
    -0.68
     kamp
    -0.68
    Bene
    -0.67
     Hodges
    -0.65
    Portale
    -0.64
     sī
    -0.63
     Mendes
    -0.63
    anelli
    -0.62
    POSITIVE LOGITS
    ']))
    1.47
    "])
    1.36
    ]))
    1.33
    ]]
    1.32
    }))
    1.30
    )
    1.29
    }]
    1.28
    )))
    1.28
    )}
    1.27
    ]
    1.27
    Act Density 0.020%

    No Known Activations