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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate limitations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urd
    -0.14
     Loose
    -0.14
    ooth
    -0.14
    ioni
    -0.13
     mixed
    -0.13
     natural
    -0.13
    ulp
    -0.13
    510
    -0.13
    emi
    -0.13
     Kirk
    -0.13
    POSITIVE LOGITS
     limited
    0.76
    limited
    0.70
     restricted
    0.70
     confined
    0.64
    restricted
    0.63
    Limited
    0.62
     Limited
    0.62
     LIMITED
    0.59
     Restricted
    0.56
    Restricted
    0.56
    Act Density 0.195%

    No Known Activations