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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions

    oai_token-act-pair · gpt-3.5-turbo

    situations involving conflict or high tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inconsistency
    -0.77
     deficits
    -0.75
     lacks
    -0.75
     mismatch
    -0.75
     conflicting
    -0.74
     shortfall
    -0.73
     inconsistent
    -0.72
    assic
    -0.71
     flaws
    -0.71
     losses
    -0.70
    POSITIVE LOGITS
     ceremon
    1.04
     proceeded
    1.03
     kissed
    0.99
     hugged
    0.98
     walked
    0.92
     kne
    0.92
     rested
    0.92
     escorted
    0.90
     instructed
    0.88
     seated
    0.88
    Act Density 0.451%

    No Known Activations