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

    Neuronpedia

    INDEX
    Explanations

    words related to confusion and perplexity

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to confusion and bewilderment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.71
    amins
    -0.71
     faire
    -0.66
    BACK
    -0.62
    ods
    -0.62
     dated
    -0.61
    Interstitial
    -0.61
     initiation
    -0.61
     amen
    -0.60
     approvals
    -0.59
    POSITIVE LOGITS
    ingly
    1.15
    stru
    0.92
     Puzz
    0.88
    azes
    0.86
     bewild
    0.82
    icably
    0.79
     awe
    0.77
     perplex
    0.76
    vu
    0.75
     amaz
    0.75
    Act Density 0.049%

    No Known Activations