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

    Neuronpedia

    INDEX
    Explanations

    syntax elements related to function definitions and annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    w
    -0.65
    er
    -0.65
    ing
    -0.63
    hu
    -0.63
    z
    -0.62
     w
    -0.61
     damn
    -0.59
     kh
    -0.58
    ed
    -0.57
     hu
    -0.57
    POSITIVE LOGITS
    ]")]
    1.82
    __":
    1.71
    }")]
    1.57
    __':
    1.48
    ')")
    1.44
    $")
    1.39
    .")]
    1.35
    }))
    1.34
     }))
    1.34
    ]$}
    1.33
    Act Density 0.035%

    No Known Activations