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

    Neuronpedia

    INDEX
    Explanations

    mentions or variations of the word "ring"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ring."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ultz
    -0.77
    merce
    -0.68
    EMP
    -0.65
    ufact
    -0.65
     Hemp
    -0.64
    ACP
    -0.64
    grown
    -0.63
    urses
    -0.60
    phies
    -0.59
     transitioning
    -0.58
    POSITIVE LOGITS
    bone
    1.01
    rings
    0.96
    naire
    0.96
    naires
    0.95
    er
    0.91
    ring
    0.90
    ettes
    0.88
    tone
    0.86
    tons
    0.84
    leader
    0.83
    Act Density 0.014%

    No Known Activations