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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mathematics and science

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistical concepts in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geries
    -0.77
    artisan
    -0.72
    panic
    -0.69
    issue
    -0.67
    rics
    -0.67
    selves
    -0.67
    scribe
    -0.63
    albeit
    -0.61
    andro
    -0.61
    andals
    -0.61
    POSITIVE LOGITS
     multiplied
    1.23
     squared
    1.22
     divided
    1.16
     minus
    0.99
    +(
    0.92
     squares
    0.87
     nearest
    0.87
    /(
    0.87
     weighted
    0.86
     calculated
    0.86
    Act Density 0.317%

    No Known Activations