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

    Neuronpedia

    INDEX
    Explanations

    references to apologies and issues of accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éri
    -0.14
    rix
    -0.14
     tear
    -0.14
    ye
    -0.14
     повеÑĢ
    -0.13
     понима
    -0.13
    rey
    -0.13
    çĤ¸
    -0.13
    ne
    -0.13
     Tib
    -0.13
    POSITIVE LOGITS
    uci
    0.16
    βι
    0.14
    OI
    0.14
    Å¡em
    0.14
    mpr
    0.13
    pong
    0.13
    enek
    0.13
    oÄŁ
    0.13
    antd
    0.13
    _probe
    0.13
    Act Density 0.006%

    No Known Activations