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

    Neuronpedia

    INDEX
    Explanations

    references to personal and political matters

    oai_token-act-pair · gpt-3.5-turbo

    references to personal and political statuses and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.84
    KER
    -0.82
    chens
    -0.72
     Mayweather
    -0.72
    ording
    -0.71
     Reloaded
    -0.70
    generic
    -0.69
     Canaver
    -0.68
    signed
    -0.68
     Helpful
    -0.68
    POSITIVE LOGITS
     arsenal
    1.33
     repertoire
    1.21
     counterparts
    1.21
     holdings
    1.18
     counterpart
    1.14
     footprint
    1.12
     woes
    1.11
     prowess
    1.09
     heritage
    1.09
     sphere
    1.06
    Act Density 0.276%

    No Known Activations