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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical damage and defects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.95
    ❋
    -0.73
    </b>
    -0.64
    fahan
    -0.63
    ongyang
    -0.62
    >--}}
    -0.59
    ()?;
    -0.58
    rinology
    -0.57
    MLLoader
    -0.57
    ModelAdmin
    -0.56
    POSITIVE LOGITS
     tearing
    1.11
     rupture
    1.06
     cracked
    1.00
     breakup
    1.00
     shattered
    0.99
     fracture
    0.99
     Cracking
    0.99
     tears
    0.98
     tear
    0.98
     Fracture
    0.97
    Act Density 0.373%

    No Known Activations