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

    Neuronpedia

    INDEX
    Explanations

    endings of sentences or phrases

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.69
     affili
    -0.67
     pit
    -0.65
     fermented
    -0.64
     prey
    -0.64
     opponent
    -0.64
     temperament
    -0.64
     accuser
    -0.63
     mosqu
    -0.62
     rept
    -0.62
    POSITIVE LOGITS
     However
    1.22
     Especially
    1.22
     Specifically
    1.16
     Whilst
    1.14
     Firstly
    1.08
     Including
    1.08
     Instead
    1.06
     Whether
    1.06
     Typically
    1.04
     Depending
    1.04
    Act Density 1.037%

    No Known Activations