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

    Neuronpedia

    INDEX
    Explanations

    mentions of superlatives indicating extreme degrees

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dale
    -0.79
    illion
    -0.78
    abin
    -0.78
    ago
    -0.74
    ship
    -0.72
    rift
    -0.72
    paren
    -0.71
    edom
    -0.71
    ilion
    -0.70
    aways
    -0.69
    POSITIVE LOGITS
     easiest
    1.19
     culmination
    1.18
     understatement
    1.10
     safest
    1.08
     simplest
    1.06
     hardest
    1.05
     cheapest
    1.04
     responsibility
    1.03
     happiest
    1.03
     busiest
    1.02
    Act Density 0.088%

    No Known Activations