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

    Neuronpedia

    INDEX
    Explanations

    phrases related to presidential terms

    oai_token-act-pair · gpt-3.5-turbo

    references to political terms and terms of office duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ECTION
    -0.72
    ICLE
    -0.71
    ideo
    -0.69
     Flavoring
    -0.67
    IDES
    -0.67
    riad
    -0.67
    rodu
    -0.67
    igious
    -0.67
    ramid
    -0.65
    LET
    -0.64
    POSITIVE LOGITS
    sworth
    0.92
    term
    0.88
     term
    0.87
    Term
    0.79
     Term
    0.76
    manship
    0.73
    mite
    0.69
    mate
    0.69
    camp
    0.68
    cycle
    0.68
    Act Density 0.007%

    No Known Activations