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

    Neuronpedia

    INDEX
    Explanations

    references to inputs and outputs in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.59
    RectangleBorder
    -0.54
     bénévol
    -0.52
    isalpha
    -0.50
     sprüche
    -0.50
     ſein
    -0.50
     GenerationType
    -0.48
    thâu
    -0.48
    startActivity
    -0.48
     SwiftUI
    -0.48
    POSITIVE LOGITS
    outputs
    0.64
    inputs
    0.63
    Outputs
    0.61
    captured
    0.55
     Outputs
    0.54
     apologise
    0.52
     excuse
    0.51
     Inputs
    0.50
    excuse
    0.49
     captures
    0.48
    Act Density 0.190%

    No Known Activations