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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.98
    InjectAttribute
    -0.91
    Autoritní
    -0.82
    PreferredItem
    -0.81
    GEBURTS
    -0.79
    تقاوى
    -0.77
    AsUp
    -0.76
     للاسماء
    -0.76
    AddTagHelper
    -0.75
    évaluateur
    -0.73
    POSITIVE LOGITS
     alike
    0.53
    ↵↵
    0.49
    getSupport
    0.43
     ces
    0.42
     respectively
    0.42
    haup
    0.41
    iland
    0.40
    ņš
    0.40
    vistar
    0.39
    <strong>
    0.38
    Act Density 0.812%

    No Known Activations