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

    Neuronpedia

    INDEX
    Explanations

    statements summarizing or reflecting on a situation or topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases that summarize or encapsulate information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cci
    -0.54
     guiIcon
    -0.53
     livest
    -0.53
     nm
    -0.52
     WARN
    -0.51
    entric
    -0.50
    MORE
    -0.49
    rang
    -0.48
    é¾įå
    -0.48
     reciproc
    -0.48
    POSITIVE LOGITS
     up
    1.94
    up
    1.57
    Up
    1.47
     Up
    1.47
    ups
    1.30
    UP
    1.29
     UP
    1.21
     ups
    1.05
     Ups
    0.84
    upt
    0.80
    Act Density 0.236%

    No Known Activations