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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and their associates

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jagu
    -0.89
    ahime
    -0.82
     à¨
    -0.79
    CAST
    -0.78
     Pu
    -0.73
    ones
    -0.73
     Pyr
    -0.72
     Curiosity
    -0.72
    TYPE
    -0.71
     Fiji
    -0.71
    POSITIVE LOGITS
    afort
    1.12
    andowski
    1.04
     Manafort
    0.91
     aide
    0.84
    oulos
    0.81
    agher
    0.78
    ossier
    0.78
    uchin
    0.75
     confid
    0.75
    eln
    0.74
    Act Density 0.025%

    No Known Activations