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

    Neuronpedia

    INDEX
    Explanations

    terms related to political supporters or customer bases

    oai_token-act-pair · gpt-3.5-turbo

    references to political or customer bases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.79
     offic
    -0.71
     ellipt
    -0.64
     abort
    -0.63
    saf
    -0.62
     revised
    -0.62
     Launcher
    -0.62
     master
    -0.59
     patents
    -0.59
    ceed
    -0.59
    POSITIVE LOGITS
     disillusion
    0.94
     discontent
    0.82
    hip
    0.80
     discont
    0.80
     hungry
    0.79
     demographics
    0.79
    untled
    0.77
     electorate
    0.77
     dissatisfaction
    0.76
     aversion
    0.76
    Act Density 0.258%

    No Known Activations