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

    Neuronpedia

    INDEX
    Explanations

    phrases related to production, results, or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    financial terms related to yield or returns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hemat
    -0.76
    zai
    -0.68
     tox
    -0.66
    alg
    -0.63
     scapego
    -0.63
    aldo
    -0.62
    ̶
    -0.61
    ovic
    -0.60
    ype
    -0.60
    uni
    -0.60
    POSITIVE LOGITS
     yield
    1.07
     yields
    0.97
     yielding
    0.89
    ENCY
    0.80
     yielded
    0.75
     highs
    0.70
     Yards
    0.69
    ensical
    0.69
    plings
    0.68
    uces
    0.68
    Act Density 0.013%

    No Known Activations