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

    Neuronpedia

    INDEX
    Explanations

    references to academic or scholarly sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StateManager
    -0.15
     Neptune
    -0.15
    nes
    -0.15
    å²Ĺ
    -0.14
    же
    -0.14
     geil
    -0.14
    .generated
    -0.14
    SSION
    -0.14
    .Css
    -0.14
    &C
    -0.14
    POSITIVE LOGITS
     Norm
    0.31
    Norm
    0.29
     Liter
    0.26
     norm
    0.25
     norms
    0.21
    Liter
    0.21
     Norman
    0.21
    norm
    0.21
     Qu
    0.21
     qu
    0.20
    Act Density 0.018%

    No Known Activations