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

    Neuronpedia

    INDEX
    Explanations

    entities related to qualities and classifications in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Baillargeon
    -0.54
     ogrod
    -0.48
     zobac
    -0.47
    InjectMocks
    -0.46
     Haaland
    -0.45
    AnimationsModule
    -0.45
    labelControl
    -0.44
    InteropServices
    -0.44
     Huan
    -0.43
     Alchemist
    -0.43
    POSITIVE LOGITS
    ury
    1.00
    ery
    0.97
    ary
    0.95
    tery
    0.93
    TERY
    0.93
    nery
    0.93
    URY
    0.93
    jiny
    0.91
    orty
    0.91
    ERY
    0.91
    Act Density 0.942%

    No Known Activations