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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to free speech and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beiter
    -0.18
    laus
    -0.15
    zano
    -0.15
    hek
    -0.14
     Episode
    -0.14
    mann
    -0.14
     blot
    -0.14
     unic
    -0.13
    _RESOLUTION
    -0.13
     wi
    -0.13
    POSITIVE LOGITS
    edom
    0.15
    ece
    0.15
    ãĥĩãĤ£ãĤ¢
    0.14
    ony
    0.14
    GameOver
    0.14
    agnostics
    0.14
     Freed
    0.14
    .Forms
    0.14
    RLF
    0.14
    ertz
    0.13
    Act Density 0.049%

    No Known Activations