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

    Neuronpedia

    INDEX
    Explanations

    terms related to socio-political issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cash
    -0.54
    INTON
    -0.54
     Stab
    -0.53
    Ze
    -0.52
    SAY
    -0.51
    IZE
    -0.51
    CI
    -0.51
     Coral
    -0.50
     Brow
    -0.50
     Walton
    -0.50
    POSITIVE LOGITS
     dominates
    1.06
     exists
    1.06
     improves
    1.04
     isn
    1.03
     tends
    1.00
     is
    0.98
     occurs
    0.98
     dictates
    0.97
     encompasses
    0.97
     involves
    0.97
    Act Density 0.445%

    No Known Activations