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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of sitting or places where sitting may occur

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raid
    -0.64
    xual
    -0.64
    Adds
    -0.62
     LOVE
    -0.59
     Scotia
    -0.59
    hiba
    -0.59
     Fighters
    -0.58
    iler
    -0.57
    AMI
    -0.56
    sha
    -0.56
    POSITIVE LOGITS
    uate
    1.32
    uating
    1.10
     ducks
    1.06
    aution
    1.06
    uated
    1.04
    uates
    1.04
    uations
    1.03
     comfortably
    0.95
    uation
    0.91
     idle
    0.89
    Act Density 0.030%

    No Known Activations