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

    Neuronpedia

    INDEX
    Explanations

    non-standard whitespace characters or formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.75
    Pare
    -0.73
     sī
    -0.71
     Bene
    -0.69
     Hodges
    -0.68
    Bene
    -0.66
     Mendes
    -0.65
     Gries
    -0.64
    èm
    -0.64
     kamp
    -0.63
    POSITIVE LOGITS
    ']))
    1.48
    "])
    1.33
    ]))
    1.32
    }))
    1.31
    )
    1.27
    ]]
    1.27
    '))
    1.27
    )))
    1.26
    "]);
    1.25
    ))
    1.25
    Act Density 0.027%

    No Known Activations