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

    Neuronpedia

    INDEX
    Explanations

    references to configurations and settings in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.66
     #
    -0.57
    <eos>
    -0.55
    ️
    -0.55
     ‘
    -0.53
    XmlEnum
    -0.53
    …)
    -0.53
     Amongst
    -0.53
    …
    -0.52
    rrggbb
    -0.52
    POSITIVE LOGITS
     pleaſure
    1.03
     purpoſe
    0.88
     fubject
    0.84
     neceſſ
    0.84
     auffi
    0.82
     étoient
    0.79
     ſind
    0.79
     poffible
    0.78
     myſelf
    0.77
     auroit
    0.77
    Act Density 0.428%

    No Known Activations