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

    Neuronpedia

    INDEX
    Explanations

    instances where something is referenced, quoted, or mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cite" and its variations, indicating references or sources in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quer
    -0.83
    ttle
    -0.81
    jah
    -0.79
    spawn
    -0.78
    ãĥĦ
    -0.77
    tail
    -0.76
    peat
    -0.75
    xy
    -0.74
    isode
    -0.74
    etheless
    -0.73
    POSITIVE LOGITS
     examples
    1.15
     inconsistencies
    1.03
     similarities
    0.97
     anecdotes
    0.96
     unnamed
    0.90
     anecdotal
    0.89
     instances
    0.88
     factors
    0.88
     studies
    0.88
     concerns
    0.88
    Act Density 0.069%

    No Known Activations