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

    Neuronpedia

    INDEX
    Explanations

    words ending with "-leaning" used to describe political orientations

    oai_token-act-pair · gpt-4-turbo

    references to political leaning or alignment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political affiliations and biases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cel
    -0.81
    cial
    -0.77
    iph
    -0.75
    cell
    -0.73
    umm
    -0.73
    ICO
    -0.73
    abe
    -0.72
    izable
    -0.72
    formance
    -0.72
    abad
    -0.72
    POSITIVE LOGITS
     leaning
    1.06
     bias
    0.76
     leans
    0.76
     lean
    0.75
     skewed
    0.75
    ©¶æ
    0.74
    leaning
    0.73
     ancest
    0.73
     favoring
    0.73
     toward
    0.73
    Act Density 0.004%

    No Known Activations