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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or superlatives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mares
    -0.88
    hm
    -0.74
    each
    -0.74
     publishes
    -0.70
     varies
    -0.69
    shaw
    -0.68
     Includes
    -0.68
    leased
    -0.68
    imi
    -0.67
    rade
    -0.66
    POSITIVE LOGITS
     culmination
    1.33
     pinnacle
    1.31
     embodiment
    1.30
     greatest
    1.19
     cornerstone
    1.18
     antidote
    1.17
     antit
    1.17
     smartest
    1.16
     gateway
    1.15
     equivalent
    1.14
    Act Density 0.189%

    No Known Activations