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

    Neuronpedia

    INDEX
    Explanations

    summaries or recaps of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to summaries and overviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liam
    -0.80
    lees
    -0.72
     Haram
    -0.68
    EED
    -0.63
     Bronze
    -0.60
    yards
    -0.59
    existent
    -0.59
    oct
    -0.59
    obyl
    -0.59
    arsity
    -0.59
    POSITIVE LOGITS
     overview
    0.95
     excerpt
    0.93
     summar
    0.84
     illustrating
    0.81
    helm
    0.81
     refres
    0.78
     explan
    0.78
     highlighting
    0.76
     summary
    0.76
     synopsis
    0.76
    Act Density 0.216%

    No Known Activations