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

    Neuronpedia

    INDEX
    Explanations

    references to speaking or speech-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <?
    -0.39
    }-${
    -0.35
     tecniche
    -0.35
    tifkan
    -0.33
     excelente
    -0.32
     Vielzahl
    -0.32
    Derbyniad
    -0.31
     Infórmanos
    -0.31
    FunctionFlags
    -0.31
     estás
    -0.31
    POSITIVE LOGITS
     frames
    0.78
     speakers
    0.75
     desk
    0.71
     Frames
    0.69
    ReusableCell
    0.66
    setVerticalGroup
    0.64
    BufferException
    0.64
    LabelTagHelper
    0.64
     speaker
    0.63
     desks
    0.62
    Act Density 0.275%

    No Known Activations