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

    Neuronpedia

    INDEX
    Explanations

    sentence endings

    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
     tremend
    -0.81
    isbury
    -0.79
     carbohyd
    -0.78
     unstoppable
    -0.72
     eleph
    -0.71
     teasp
    -0.71
    ceivable
    -0.71
     electr
    -0.71
     unseen
    -0.70
     uncontroll
    -0.70
    POSITIVE LOGITS
     Anyway
    2.06
     Nonetheless
    1.77
     Nevertheless
    1.66
    Anyway
    1.61
     Regardless
    1.56
     However
    1.41
     Either
    1.38
     Still
    1.38
     Otherwise
    1.36
     Also
    1.35
    Act Density 0.532%

    No Known Activations