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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    contextual references to significant historical events and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ?)
    -1.04
    -)
    -1.03
    )?
    -1.01
    ?]
    -1.00
    ?),
    -0.93
    ?).
    -0.90
    ?)
    -0.90
    })
    -0.78
    )}
    -0.72
    )\
    -0.70
    POSITIVE LOGITS
    .
    0.81
    .[
    0.66
     residing
    0.65
     consisting
    0.63
     located
    0.63
     pertaining
    0.62
    *.
    0.61
     utilizing
    0.61
     stemming
    0.60
     resulting
    0.59
    Act Density 1.603%

    No Known Activations