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

    Neuronpedia

    INDEX
    Explanations

    sentences that end in periods

    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
    etheless
    -0.79
     affili
    -0.72
     exting
    -0.69
     conclud
    -0.69
     suspic
    -0.68
     derog
    -0.67
     quir
    -0.67
     volunte
    -0.66
     vo
    -0.66
     stocking
    -0.66
    POSITIVE LOGITS
     Lots
    1.41
     Everybody
    1.39
     Everything
    1.34
     We
    1.33
     Everyone
    1.32
     Literally
    1.31
     They
    1.30
     There
    1.30
     Everywhere
    1.25
     Firstly
    1.25
    Act Density 0.376%

    No Known Activations