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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political discourse and argumentation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to critique or criticism of societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĺãĥ©
    -0.84
    elta
    -0.80
    SEA
    -0.79
    significant
    -0.78
    uilt
    -0.74
    emale
    -0.74
    ousands
    -0.73
    inia
    -0.72
    OTOS
    -0.71
    ĻĤ
    -0.70
    POSITIVE LOGITS
     nonsense
    0.97
     spew
    0.90
     bullshit
    0.87
     antics
    0.87
     excuse
    0.87
     brav
    0.87
     shenanigans
    0.86
     tactics
    0.84
     clich
    0.80
     arrogance
    0.80
    Act Density 0.312%

    No Known Activations