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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.86
     agre
    -0.72
     SPI
    -0.69
     Authent
    -0.65
     redes
    -0.65
     Gentleman
    -0.64
     Voices
    -0.62
     corrid
    -0.61
     whistle
    -0.61
     therap
    -0.61
    POSITIVE LOGITS
    frac
    0.97
    âĪĴ
    0.93
    cos
    0.82
    ((
    0.78
     âĪĴ
    0.77
    (-
    0.76
    }}
    0.76
    Solution
    0.75
    λ
    0.75
    Ïī
    0.75
    Act Density 0.091%

    No Known Activations