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

    Neuronpedia

    INDEX
    Explanations

    terms associated with negative health outcomes and dysfunction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.70
     ArrayAdapter
    -0.59
     doInBackground
    -0.58
    ondis
    -0.57
    assertNotNull
    -0.56
     تضيفلها
    -0.55
     Leich
    -0.54
     dusting
    -0.53
     Humboldt
    -0.52
    udesta
    -0.52
    POSITIVE LOGITS
    👎
    0.89
     bad
    0.86
     worse
    0.81
    bad
    0.76
     mauvaise
    0.74
     rossz
    0.71
     mauvais
    0.68
     worst
    0.68
     badly
    0.67
    worse
    0.67
    Act Density 0.772%

    No Known Activations