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

    Neuronpedia

    INDEX
    Explanations

    information related to detailed measurements or distances

    oai_token-act-pair · gpt-3.5-turbo

    references to pledging or supporting projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Woody
    -0.64
    uv
    -0.62
     masculinity
    -0.62
     Chomsky
    -0.60
     deport
    -0.58
     bodily
    -0.56
    politics
    -0.56
    animate
    -0.56
     Born
    -0.54
     Kissinger
    -0.54
    POSITIVE LOGITS
    .).
    0.88
    )).
    0.84
    `.
    0.82
    >.
    0.82
    }.
    0.82
    !).
    0.77
    ]).
    0.76
    ().
    0.75
     ).
    0.72
    .</
    0.72
    Act Density 1.460%

    No Known Activations