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

    Neuronpedia

    INDEX
    Explanations

    trademarks or registered symbols

    oai_token-act-pair · gpt-3.5-turbo

    trademark symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.93
    vernment
    -0.72
     sqor
    -0.68
    */(
    -0.68
    selage
    -0.68
    ships
    -0.65
     soup
    -0.62
     young
    -0.61
    byss
    -0.61
     compress
    -0.59
    POSITIVE LOGITS
    TM
    1.15
    obile
    0.87
    ucci
    0.87
    ategory
    0.83
    RC
    0.82
    obiles
    0.81
    ovember
    0.80
    asters
    0.79
    astic
    0.77
    astics
    0.76
    Act Density 0.008%

    No Known Activations