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

    Neuronpedia

    INDEX
    Explanations

    news headlines related to various events and crises

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iage
    -0.79
    adra
    -0.78
    ©¶æ¥µ
    -0.76
     externalToEVAOnly
    -0.69
    owment
    -0.69
    yss
    -0.69
    gat
    -0.69
    uchi
    -0.66
    transfer
    -0.65
    ledged
    -0.65
    POSITIVE LOGITS
     highlights
    0.95
     reveals
    0.94
     listener
    0.92
     Highlights
    0.91
    podcast
    0.91
     discusses
    0.89
     topics
    0.89
     Spoiler
    0.88
     spoiler
    0.88
     fascinating
    0.86
    Act Density 2.669%

    No Known Activations