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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dates or events

    oai_token-act-pair · gpt-3.5-turbo

    sentences or statements, particularly those that express hope or wishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proport
    -0.89
     tremend
    -0.89
     challeng
    -0.80
     stringent
    -0.79
     exha
    -0.78
     cumbers
    -0.74
    quartered
    -0.74
    ascus
    -0.74
     carbohyd
    -0.74
     involuntary
    -0.74
    POSITIVE LOGITS
    <|endoftext|>
    1.91
     ®
    1.87
     Hopefully
    1.49
     Stay
    1.28
     Until
    1.23
     Perhaps
    1.22
    Advertisements
    1.22
     ðŁĻĤ
    1.18
     Especially
    1.17
     Maybe
    1.17
    Act Density 0.461%

    No Known Activations