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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related events/actions

    oai_token-act-pair · gpt-3.5-turbo

    events and actions that signify significant changes or occurrences in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )}
    -0.83
    )",
    -0.76
    }"
    -0.74
    )"
    -0.73
    )+
    -0.71
    )).
    -0.71
     recent
    -0.71
    }}}
    -0.69
     avoided
    -0.69
     ));
    -0.68
    POSITIVE LOGITS
     again
    1.07
     anew
    1.04
     aboard
    0.83
    again
    0.81
     onstage
    0.80
     triumphant
    0.76
     formally
    0.76
     atop
    0.73
     triumph
    0.72
     abruptly
    0.72
    Act Density 0.638%

    No Known Activations