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

    Neuronpedia

    INDEX
    Explanations

    specific programming constructs and operations in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Incomplete
    -0.60
    catching
    -0.58
     bricolaje
    -0.58
     ansch
    -0.54
    inducing
    -0.54
     Incomplete
    -0.53
    incomplete
    -0.53
    activating
    -0.52
    ype
    -0.52
    iora
    -0.50
    POSITIVE LOGITS
     disambiguazione
    0.84
     raiſ
    0.79
    parsedMessage
    0.74
     edited
    0.72
     cated
    0.71
     geï
    0.70
    posedge
    0.69
    AsUp
    0.67
     ddelweddau
    0.65
     memoized
    0.65
    Act Density 0.488%

    No Known Activations