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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methodologies and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.98
     CreateTagHelper
    -0.95
     GenerationType
    -0.89
    AddTagHelper
    -0.88
     ProtoMessage
    -0.85
    posedge
    -0.83
     تضيفلها
    -0.83
     الحره
    -0.83
    Personensuche
    -0.83
    horabuena
    -0.81
    POSITIVE LOGITS
    直
    0.46
     then
    0.45
    del
    0.43
    chii
    0.41
    instein
    0.40
    olo
    0.40
    ys
    0.40
    AppendLine
    0.39
    gel
    0.39
     Sen
    0.38
    Act Density 1.568%

    No Known Activations