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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.60
     cruc
    -0.59
     Mouse
    -0.58
     Rabbit
    -0.56
     ribbon
    -0.56
     tur
    -0.55
     pandemonium
    -0.55
    ãĤ¤
    -0.55
     fined
    -0.55
    POSITIVE LOGITS
    S
    1.35
    N
    1.20
    K
    0.94
    $.
    0.93
    NAT
    0.91
     Nations
    0.89
    NER
    0.87
    SI
    0.86
    Ns
    0.84
    zbek
    0.80
    Act Density 0.042%

    No Known Activations