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

    Neuronpedia

    INDEX
    Explanations

    words associated with names, locations, and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doll
    -0.46
     betreft
    -0.46
    \":\"
    -0.46
    ß
    -0.45
     "{\"
    -0.44
     Abingdon
    -0.44
    cliff
    -0.43
    př
    -0.42
    ř
    -0.42
     :—
    -0.42
    POSITIVE LOGITS
    AutoField
    0.66
     Duggan
    0.65
     onOptions
    0.64
    CppMethod
    0.63
    fontWeight
    0.62
    Gadget
    0.61
     Gadget
    0.59
     Wolfe
    0.57
     Regie
    0.57
    isEmail
    0.56
    Act Density 3.225%

    No Known Activations