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

    Neuronpedia

    INDEX
    Explanations

    mentions of celebrities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.21
    MOVED
    -0.15
    maze
    -0.15
    istrovstvÃŃ
    -0.15
    edImage
    -0.15
    mul
    -0.14
    ť
    -0.14
    iciel
    -0.14
    neau
    -0.14
    ayd
    -0.14
    POSITIVE LOGITS
    brities
    0.28
    stial
    0.23
     cele
    0.22
    -ce
    0.22
    brate
    0.21
     Cele
    0.21
    brit
    0.20
    ste
    0.18
    cele
    0.17
    Cele
    0.17
    Act Density 0.004%

    No Known Activations