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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize specific points or details within a discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     experience
    -0.76
     each
    -0.75
     then
    -0.74
     no
    -0.69
     identical
    -0.69
     failed
    -0.69
     undisclosed
    -0.67
     another
    -0.67
     prest
    -0.67
     expired
    -0.67
    POSITIVE LOGITS
     Especially
    3.06
    Especially
    2.79
     Particularly
    2.38
    especially
    2.26
    particularly
    1.73
     Including
    1.56
     Unless
    1.48
    icularly
    1.35
    Unless
    1.30
     Besides
    1.29
    Act Density 0.028%

    No Known Activations