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

    Neuronpedia

    INDEX
    Explanations

    references to internal processes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.65
    endphp
    -0.63
     gages
    -0.56
    TypedDataSet
    -0.56
    rophoresis
    -0.56
     pleaſure
    -0.55
    parsedMessage
    -0.52
    <?
    -0.52
     getRule
    -0.52
    ագրություններ
    -0.52
    POSITIVE LOGITS
     internal
    2.28
    internal
    2.14
    Internal
    2.13
     Internal
    2.11
     INTERNAL
    1.87
    INTERNAL
    1.86
     internally
    1.79
     interno
    1.39
     internes
    1.38
     external
    1.37
    Act Density 0.098%

    No Known Activations