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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities preceded by a symbol representing currency

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lass
    -0.78
    ares
    -0.66
    NULL
    -0.65
    });
    -0.65
    comfort
    -0.64
    without
    -0.64
    death
    -0.63
    chrome
    -0.62
    ]}
    -0.60
    jen
    -0.59
    POSITIVE LOGITS
     exception
    0.88
     emphasis
    0.88
     exceptions
    0.86
     notable
    0.83
     caveat
    0.80
     intervening
    0.76
    phasis
    0.73
     caveats
    0.72
     consequ
    0.72
     doubling
    0.72
    Act Density 0.288%

    No Known Activations