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

    Neuronpedia

    INDEX
    Explanations

    the word "arbitrary" appearing with different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of arbitrariness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosis
    -0.89
    ien
    -0.85
    icans
    -0.84
    iao
    -0.81
    oir
    -0.80
    lain
    -0.79
    ilitating
    -0.78
    iens
    -0.76
    ership
    -0.76
    iquette
    -0.74
    POSITIVE LOGITS
     whims
    0.92
     guiActiveUn
    0.91
     arbitrary
    0.85
     extr
    0.77
     drift
    0.72
     shortcuts
    0.70
     comput
    0.70
     pret
    0.69
     boundaries
    0.68
     slab
    0.68
    Act Density 0.016%

    No Known Activations