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

    Neuronpedia

    INDEX
    Explanations

    dates and locations mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to publication dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.71
    antha
    -0.61
    Joined
    -0.60
    etheless
    -0.59
     secondly
    -0.59
    yip
    -0.58
     disadvant
    -0.56
    Reviewer
    -0.55
     '.
    -0.53
    ,,,,
    -0.53
    POSITIVE LOGITS
    PIN
    0.70
    PN
    0.65
    eling
    0.65
    PD
    0.62
    gan
    0.61
    )
    0.61
    NPR
    0.59
    amily
    0.59
    illance
    0.58
    PHOTOS
    0.55
    Act Density 0.038%

    No Known Activations