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

    Neuronpedia

    INDEX
    Explanations

    specific programming constructs and comparisons, particularly conditional checks and equality statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     their
    -0.45
     they
    -0.44
     now
    -0.43
     th
    -0.43
    ↵
    -0.42
    あら
    -0.42
    now
    -0.42
    ans
    -0.42
     S
    -0.41
    fehl
    -0.41
    POSITIVE LOGITS
    requestCode
    1.07
     pleaſure
    0.93
     Efq
    0.89
     chofe
    0.86
     WaitForSeconds
    0.84
    исленность
    0.83
    featureID
    0.82
     poffe
    0.80
     AssemblyTitle
    0.80
     fubject
    0.80
    Act Density 0.095%

    No Known Activations