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

    Neuronpedia

    INDEX
    Explanations

    references to headlines and their impact on media narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erdale
    -0.14
    anian
    -0.14
    _OC
    -0.13
    SEQUENTIAL
    -0.13
     loa
    -0.13
     Standing
    -0.13
    ola
    -0.13
    ulary
    -0.13
    ifo
    -0.13
    .ul
    -0.13
    POSITIVE LOGITS
     Polo
    0.17
    headline
    0.16
     kra
    0.15
     Verm
    0.15
    reek
    0.15
    å¼ı
    0.14
    knife
    0.14
    igest
    0.14
    ateway
    0.14
     headlines
    0.14
    Act Density 0.018%

    No Known Activations