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

    Neuronpedia

    INDEX
    Explanations

    references to accountability and critique of moral behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.69
     EconPapers
    -0.60
     ſta
    -0.49
    AnimationsModule
    -0.48
     vettoriale
    -0.48
     BufferedWriter
    -0.47
     ſch
    -0.46
     queſta
    -0.46
     tranſ
    -0.46
     onCreateView
    -0.45
    POSITIVE LOGITS
     i
    1.00
     ir
    0.89
    iI
    0.74
     ii
    0.73
     il
    0.72
    i
    0.70
     iti
    0.70
     Ii
    0.68
     Ir
    0.66
     im
    0.65
    Act Density 0.427%

    No Known Activations