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

    Neuronpedia

    INDEX
    Explanations

    phrases that express likelihood or certainty about a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELD
    -0.65
    anza
    -0.62
    ollar
    -0.62
    ENCY
    -0.62
     Skydragon
    -0.61
     Distance
    -0.61
    imeters
    -0.60
     MAC
    -0.58
    alky
    -0.56
    ropy
    -0.55
    POSITIVE LOGITS
     unsur
    0.99
     understandable
    0.79
     logical
    0.77
    chwitz
    0.76
    worthiness
    0.75
     surprising
    0.75
     logically
    0.75
     deserving
    0.75
     fitting
    0.72
     merits
    0.72
    Act Density 0.844%

    No Known Activations