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

    Neuronpedia

    INDEX
    Explanations

    terms related to levels of intensity or significance

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that describe the manner of actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cade
    -0.72
    arya
    -0.71
    eto
    -0.67
     Majority
    -0.67
    retty
    -0.67
     Voy
    -0.64
    uese
    -0.64
     Timbers
    -0.64
    hyde
    -0.63
     Payne
    -0.63
    POSITIVE LOGITS
     spaced
    0.90
    protected
    0.77
     constructed
    0.75
     educated
    0.73
     insignificant
    0.73
     vaccinated
    0.71
     overlapping
    0.70
     defined
    0.70
     separated
    0.70
     placed
    0.70
    Act Density 0.166%

    No Known Activations