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

    Neuronpedia

    INDEX
    Explanations

    specific details or components within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal and bureaucratic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     .)
    -0.76
    .--
    -0.70
     |
    -0.65
    .)
    -0.64
    .]
    -0.62
    .):
    -0.61
    urden
    -0.61
    ettle
    -0.61
    --
    -0.59
    ---
    -0.59
    POSITIVE LOGITS
     etc
    0.92
     srf
    0.89
     carbohyd
    0.76
    etc
    0.71
     captcha
    0.71
     tradem
    0.68
    anwhile
    0.68
     segregated
    0.66
     compr
    0.66
     assorted
    0.65
    Act Density 0.353%

    No Known Activations