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

    Neuronpedia

    INDEX
    Explanations

    instances of political hypocrisy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     generations
    -0.17
    allet
    -0.14
    ä¸ĸç´Ģ
    -0.14
    sha
    -0.14
    zend
    -0.14
    ahir
    -0.14
    inya
    -0.14
    åĵŃ
    -0.13
    हर
    -0.13
    _SYM
    -0.13
    POSITIVE LOGITS
     Cabinet
    0.18
     accomplishments
    0.18
     White
    0.17
     cabinet
    0.17
     performance
    0.17
     Performance
    0.16
     Omn
    0.16
    绩
    0.16
    0.15
     âĺħ
    0.15
    Act Density 0.121%

    No Known Activations