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

    Neuronpedia

    INDEX
    Explanations

    specific activities or events that took place

    oai_token-act-pair · gpt-3.5-turbo

    references to social media activities and incidents involving public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "))
    -0.63
    )).
    -0.60
     ])
    -0.59
    })
    -0.59
    ]).
    -0.57
    });
    -0.56
     dele
    -0.55
    akers
    -0.53
    ĪĴ
    -0.52
    ao
    -0.52
    POSITIVE LOGITS
     shortly
    0.91
     insofar
    0.87
     via
    0.86
     because
    0.86
     sometime
    0.84
     alongside
    0.81
     along
    0.75
     primarily
    0.75
     pursuant
    0.75
     although
    0.74
    Act Density 1.112%

    No Known Activations