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

    Neuronpedia

    INDEX
    Explanations

    words related to political positions or stances on various issues

    oai_token-act-pair · gpt-3.5-turbo

    references to political positions or stances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennes
    -0.76
    Champ
    -0.72
    Chel
    -0.69
    à¨
    -0.67
    agar
    -0.64
    INESS
    -0.64
    aniel
    -0.63
    @@@@
    -0.62
    flies
    -0.62
    anova
    -0.61
    POSITIVE LOGITS
     behalf
    1.59
    erous
    0.99
     matters
    0.90
    yx
    0.89
     occasion
    0.87
     steroids
    0.85
    shore
    0.83
     Capitol
    0.81
    eworld
    0.81
    eness
    0.80
    Act Density 0.203%

    No Known Activations