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

    Neuronpedia

    INDEX
    Explanations

    phrases related to showcasing or displaying something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "show off."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hai
    -0.70
     ISI
    -0.66
    obs
    -0.65
    CU
    -0.65
     cogn
    -0.63
    ĪĴ
    -0.62
    externalActionCode
    -0.62
    oked
    -0.60
    Bridge
    -0.59
    ombs
    -0.58
    POSITIVE LOGITS
    ments
    0.80
    ishly
    0.73
     DEF
    0.71
    iveness
    0.68
    nces
    0.67
    rey
    0.65
    ment
    0.64
    MENT
    0.63
     spoilers
    0.63
    mented
    0.63
    Act Density 0.016%

    No Known Activations