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

    Neuronpedia

    INDEX
    Explanations

    words associated with medical diagnoses or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.08
    3:0.06
    4:0.08
    5:0.02
    6:0.09
    7:0.37
    8:0.03
    9:0.03
    10:0.13
    11:0.03
    Negative Logits
    soDeliveryDate
    -2.10
     tailored
    -1.71
    requires
    -1.69
    furt
    -1.67
     concise
    -1.66
     crafted
    -1.65
     challeng
    -1.56
    annis
    -1.56
    chel
    -1.54
    minus
    -1.52
    POSITIVE LOGITS
     laure
    1.78
     deform
    1.67
     rall
    1.64
     confidentiality
    1.60
     preservation
    1.58
     solitude
    1.57
     Happiness
    1.56
    ynchron
    1.54
     recovery
    1.50
    Storage
    1.49
    Act Density 0.000%

    No Known Activations