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

    Neuronpedia

    INDEX
    Explanations

    economic indicators such as price and inflation changes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "rose" and its variations to indicate increases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Founding
    -0.77
    tta
    -0.70
    pora
    -0.70
    sol
    -0.68
    mates
    -0.68
    mir
    -0.67
    ãĥīãĥ©
    -0.66
    è»
    -0.66
    mate
    -0.64
    Fail
    -0.63
    POSITIVE LOGITS
     sharply
    0.95
     steadily
    0.86
     dramatically
    0.86
     exponentially
    0.80
     enormously
    0.79
     explos
    0.78
     substantially
    0.78
     markedly
    0.78
     tremendously
    0.77
     immensely
    0.77
    Act Density 0.116%

    No Known Activations