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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advoc
    -0.90
     concess
    -0.79
    igham
    -0.76
     elim
    -0.76
    yip
    -0.74
    inav
    -0.74
     warr
    -0.74
     compr
    -0.69
     discour
    -0.67
     lump
    -0.67
    POSITIVE LOGITS
    <|endoftext|>
    1.21
     Because
    1.15
     According
    1.08
     Especially
    1.03
     Journalists
    1.00
     Soon
    1.00
     Though
    0.99
     Until
    0.98
     ®
    0.98
     Shortly
    0.96
    Act Density 0.450%

    No Known Activations