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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics and government actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of leadership and action in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dunno
    -0.81
     Likes
    -0.69
     Cue
    -0.67
    might
    -0.67
     Alternatively
    -0.63
     rumours
    -0.63
    arently
    -0.63
    usually
    -0.63
     Possibly
    -0.62
     Presumably
    -0.61
    POSITIVE LOGITS
    .","
    1.16
    "}],"
    0.97
    .''
    0.96
    !"
    0.91
    ."
    0.90
    !!"
    0.90
    .""
    0.89
     wherever
    0.87
    redible
    0.84
     statewide
    0.83
    Act Density 0.524%

    No Known Activations