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

    Neuronpedia

    INDEX
    Explanations

    words related to confusion, perplexity, and bewilderment

    oai_token-act-pair · gpt-3.5-turbo

    words that express confusion or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equity
    -0.68
     bye
    -0.67
     faire
    -0.65
     Policies
    -0.62
     subcontract
    -0.62
     Rover
    -0.62
     RL
    -0.61
     Order
    -0.61
     allowance
    -0.60
     approved
    -0.60
    POSITIVE LOGITS
    ingly
    1.58
    stru
    1.00
    ulous
    0.93
    ienced
    0.91
    ibly
    0.89
    ience
    0.88
    iously
    0.87
    ace
    0.87
    azes
    0.87
    ible
    0.87
    Act Density 0.088%

    No Known Activations