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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong opinions or statements by using words like "called," "condemned," or "rejected."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the verb "call" or its variations, often in the context of labeling or defining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.72
    ondo
    -0.68
    azon
    -0.67
    ainer
    -0.66
    ATCH
    -0.66
    entity
    -0.65
    rers
    -0.64
    iland
    -0.64
    folder
    -0.63
    ã
    -0.63
    POSITIVE LOGITS
     "
    0.73
     constructive
    0.72
     systemic
    0.69
     Byzantine
    0.67
     insur
    0.65
     flaws
    0.64
     compromises
    0.64
     deficiencies
    0.63
     shortcomings
    0.62
     archaic
    0.61
    Act Density 0.057%

    No Known Activations