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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a full stop

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     salute
    -0.77
     lifes
    -0.67
    amaru
    -0.67
     synerg
    -0.65
     stride
    -0.64
    stre
    -0.64
     saving
    -0.63
     convoy
    -0.62
     bonus
    -0.62
    ozyg
    -0.62
    POSITIVE LOGITS
     Specifically
    1.29
     Certainly
    1.26
     Initially
    1.23
     Some
    1.19
     Firstly
    1.18
     Ultimately
    1.18
     Whether
    1.17
     Generally
    1.15
     Personally
    1.15
     Currently
    1.14
    Act Density 0.415%

    No Known Activations