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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical details and specifications

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation and the context surrounding statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     earthqu
    -0.77
     advoc
    -0.74
     enthusi
    -0.72
     pione
    -0.72
     captcha
    -0.71
    MpServer
    -0.71
    Ü
    -0.69
     tyr
    -0.69
    âĵĺ
    -0.69
    Þ
    -0.69
    POSITIVE LOGITS
     Consequently
    1.50
     Therefore
    1.44
     Moreover
    1.41
     Nonetheless
    1.39
     Hence
    1.34
     Nevertheless
    1.34
     Furthermore
    1.31
     Likewise
    1.31
     Similarly
    1.28
     So
    1.24
    Act Density 0.521%

    No Known Activations