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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods, indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stranger
    -0.69
     mosqu
    -0.68
     cradle
    -0.64
     mate
    -0.63
    onga
    -0.63
     brut
    -0.62
     glim
    -0.62
    ãĤ©
    -0.61
    itaire
    -0.61
     assassin
    -0.60
    POSITIVE LOGITS
     They
    0.99
     Whilst
    0.96
     However
    0.94
     Besides
    0.93
     Additionally
    0.92
     Though
    0.91
     Although
    0.91
     Depending
    0.91
     Their
    0.90
     These
    0.90
    Act Density 0.500%

    No Known Activations