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

    Neuronpedia

    INDEX
    Explanations

    technical references or mentions of programming languages and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.92
    ſelves
    -0.84
    ſelf
    -0.79
     pleaſure
    -0.79
    ]")]
    -0.78
    ".
    -0.77
    iastes
    -0.76
     poffible
    -0.75
    вгений
    -0.74
     AssemblyCulture
    -0.73
    POSITIVE LOGITS
    (?)
    0.86
     IIRC
    0.85
     iirc
    0.83
     (?)
    0.81
     pretty
    0.78
     apparently
    0.76
     basically
    0.74
     actually
    0.69
     supposedly
    0.67
    basically
    0.65
    Act Density 0.605%

    No Known Activations