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

    Neuronpedia

    INDEX
    Explanations

    academic positions and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of academic institutions and their associated faculty or departments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     awa
    -0.51
     hump
    -0.49
     robbers
    -0.48
     condom
    -0.47
     headlights
    -0.47
     silence
    -0.46
     selfie
    -0.44
     withdrawals
    -0.44
     footprints
    -0.44
     backwards
    -0.44
    POSITIVE LOGITS
    .).
    0.68
    ]).
    0.63
    )).
    0.62
    ]),
    0.61
    ).
    0.58
     )]
    0.56
    )),
    0.56
    )]
    0.54
     Synd
    0.53
    thur
    0.53
    Act Density 1.264%

    No Known Activations