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

    Neuronpedia

    INDEX
    Explanations

    the verb "is" followed by another word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    statements that assert the existence or nature of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iard
    -0.87
    eor
    -0.78
    agues
    -0.75
    ventures
    -0.67
    luaj
    -0.65
    ievers
    -0.65
    iovascular
    -0.64
    stad
    -0.63
    vantage
    -0.62
    avored
    -0.62
    POSITIVE LOGITS
     something
    0.90
     nothing
    0.86
     extraordinary
    0.80
     undeniable
    0.80
     astounding
    0.80
     exactly
    0.78
     somebody
    0.77
     basically
    0.76
     remarkable
    0.75
     essentially
    0.74
    Act Density 0.095%

    No Known Activations