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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation or formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goy
    -0.71
    émon
    -0.66
     Dol
    -0.66
    tish
    -0.64
     climate
    -0.63
     Hau
    -0.63
    FORME
    -0.63
     phi
    -0.62
    umph
    -0.61
    Ə
    -0.61
    POSITIVE LOGITS
    ])
    1.52
    }))
    1.47
    ]")]
    1.46
    })
    1.44
    €)
    1.37
    ())
    1.37
    '])
    1.36
    >)
    1.35
    ))
    1.35
    __)
    1.33
    Act Density 0.321%

    No Known Activations