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

    Neuronpedia

    INDEX
    Explanations

    the term "int" in various contexts related to intelligence or indicating interactivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     èı
    -0.15
    ovice
    -0.15
    มà¸Ļ
    -0.15
    agus
    -0.14
    alen
    -0.14
    inition
    -0.14
    orpion
    -0.14
     swirl
    -0.14
    κÎŃ
    -0.14
    irling
    -0.14
    POSITIVE LOGITS
    erg
    0.27
    roducing
    0.27
    ’l
    0.27
    ensive
    0.25
    'l
    0.23
    erc
    0.23
    ers
    0.22
    ended
    0.21
    egrate
    0.20
    erm
    0.20
    Act Density 0.009%

    No Known Activations