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

    Neuronpedia

    INDEX
    Explanations

    references to anonymity and the protection of personal information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rench
    -0.17
     unf
    -0.15
    enes
    -0.15
    -0.14
     Lou
    -0.14
    istrar
    -0.14
    VP
    -0.14
    neau
    -0.13
    anas
    -0.13
     units
    -0.13
    POSITIVE LOGITS
    ERY
    0.17
    odÃŃ
    0.15
    luv
    0.15
    orks
    0.15
    è·
    0.15
    _FILL
    0.15
    ordon
    0.14
    ازÙħ
    0.14
     Cair
    0.14
    _UNLOCK
    0.14
    Act Density 0.024%

    No Known Activations