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

    Neuronpedia

    INDEX
    Explanations

    phrases related to creation, construction, and organization

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with creation, construction, and composition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RESULTS
    -0.69
     Carbuncle
    -0.62
    tein
    -0.58
     Sierra
    -0.57
     Tropical
    -0.57
     Flavoring
    -0.57
     reviewer
    -0.57
     Sack
    -0.57
     Stim
    -0.56
    hus
    -0.56
    POSITIVE LOGITS
     differently
    0.99
    entious
    0.90
    hematically
    0.85
    ependent
    0.79
     inconsist
    0.79
    ividually
    0.79
    ptin
    0.79
    angering
    0.77
     somew
    0.76
     elsewhere
    0.76
    Act Density 0.292%

    No Known Activations