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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questioning or seeking to understand different perspectives or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.75
     encounters
    -0.71
    obbies
    -0.70
     wills
    -0.69
     stalls
    -0.67
     Nightmares
    -0.66
    itches
    -0.66
    aneers
    -0.65
     hours
    -0.64
     credits
    -0.63
    POSITIVE LOGITS
    olation
    1.28
    olated
    1.22
    olate
    1.14
    rael
    1.02
    peria
    0.98
    nt
    0.95
    terness
    0.93
    omorphic
    0.90
    htar
    0.88
    abella
    0.87
    Act Density 0.215%

    No Known Activations