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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong positive affection or admiration towards something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enthusiasm or admiration for various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tents
    -0.64
     equival
    -0.62
     transitions
    -0.61
     desks
    -0.61
     incompet
    -0.60
     futures
    -0.60
    spection
    -0.59
     roofs
    -0.59
    acements
    -0.59
     torches
    -0.59
    POSITIVE LOGITS
     of
    1.04
    76561
    0.87
    atical
    0.84
    oft
    0.78
     Of
    0.78
     OF
    0.77
    ledged
    0.77
     thereof
    0.72
    wart
    0.71
     favorite
    0.69
    Act Density 0.079%

    No Known Activations