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

    Neuronpedia

    INDEX
    Explanations

    JavaScript syntax and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    code-related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ido
    -0.70
    est
    -0.65
    ifying
    -0.65
    reen
    -0.61
    ened
    -0.60
    acre
    -0.60
    aband
    -0.60
    azing
    -0.59
    hor
    -0.59
    ware
    -0.59
    POSITIVE LOGITS
    {{
    1.07
    }}
    1.06
    }}}
    0.93
    utical
    0.93
     STATS
    0.90
    illac
    0.88
    phrine
    0.87
     {{
    0.80
    âĨij
    0.79
     "$:/
    0.79
    Act Density 0.012%

    No Known Activations