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

    Neuronpedia

    INDEX
    Explanations

    sentences related to government policies and actions

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding budget-related commitments and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prank
    -0.75
     celeb
    -0.70
    ĸļ
    -0.70
     cameo
    -0.69
     hilar
    -0.67
     Kardashian
    -0.67
     nude
    -0.67
     featured
    -0.67
     amused
    -0.65
     Released
    -0.64
    POSITIVE LOGITS
    Secondly
    1.05
    Govern
    1.00
    âĢİ
    0.99
    We
    0.98
     we
    0.96
    we
    0.93
     secondly
    0.93
    rastructure
    0.92
    America
    0.91
    Economic
    0.88
    Act Density 0.426%

    No Known Activations