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

    Neuronpedia

    INDEX
    Explanations

    references to things being arbitrary or done without a specific reason

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "arbitrary" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oir
    -0.88
    icans
    -0.88
    iosis
    -0.86
    ership
    -0.86
    iao
    -0.86
    iere
    -0.79
    amen
    -0.79
    ieri
    -0.78
    lain
    -0.77
    tha
    -0.76
    POSITIVE LOGITS
     guiActiveUn
    0.94
     whims
    0.91
     arbitrary
    0.86
    judicial
    0.74
     recomp
    0.73
     whim
    0.71
     extr
    0.71
     confinement
    0.70
     drift
    0.70
     pret
    0.69
    Act Density 0.020%

    No Known Activations