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

    Neuronpedia

    INDEX
    Explanations

    references to official governing bodies or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.73
     nahilalakip
    -0.73
    AnimationsModule
    -0.72
     GenerationType
    -0.68
    withIdentifier
    -0.66
     BorderSide
    -0.65
    ftagPool
    -0.65
    awtextra
    -0.63
     chré
    -0.62
    WithMany
    -0.62
    POSITIVE LOGITS
     proving
    0.66
     dial
    0.66
     Dial
    0.51
     proves
    0.50
     authorities
    0.48
     prove
    0.47
     dials
    0.43
     gus
    0.42
     constitutes
    0.42
     constitute
    0.41
    Act Density 0.259%

    No Known Activations