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

    Neuronpedia

    INDEX
    Explanations

    references to buttons or button-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TestBed
    -0.62
    erweise
    -0.61
     RISE
    -0.55
    glLoadIdentity
    -0.52
    gwick
    -0.52
    ãng
    -0.51
    OrWhiteSpace
    -0.50
    modelBuilder
    -0.50
     NgModule
    -0.50
    rinfo
    -0.49
    POSITIVE LOGITS
     buttons
    1.67
     Buttons
    1.50
     button
    1.34
    buttons
    1.32
     btn
    1.24
     Button
    1.24
     BUTTON
    1.23
    Buttons
    1.23
    button
    1.15
    BUTTON
    1.13
    Act Density 0.102%

    No Known Activations