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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to food items and naval terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteLiteral
    -0.83
     Samara
    -0.77
     MDR
    -0.74
     Bogen
    -0.73
     noten
    -0.73
    Juliet
    -0.69
     Stratton
    -0.69
     Schmid
    -0.69
    Boh
    -0.66
     ögon
    -0.65
    POSITIVE LOGITS
     Falk
    1.00
    Falk
    0.88
     Phillies
    0.85
    ReusableCell
    0.85
     Fizz
    0.83
     Baird
    0.83
     ctypes
    0.82
     Fries
    0.82
     Sard
    0.80
     Falkland
    0.80
    Act Density 2.001%

    No Known Activations