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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events being done or happening

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "was" and its variations in tense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    future
    -0.69
    ties
    -0.63
     newsletters
    -0.62
    VILLE
    -0.61
    feel
    -0.57
     universes
    -0.56
     Limits
    -0.56
    Use
    -0.56
    acers
    -0.56
    negative
    -0.55
    POSITIVE LOGITS
     commissioned
    1.26
     conceived
    1.26
     devised
    1.26
     initiated
    1.24
     created
    1.24
     spearheaded
    1.23
     launched
    1.21
     originally
    1.21
     inspired
    1.20
     authored
    1.19
    Act Density 0.181%

    No Known Activations