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

    Neuronpedia

    INDEX
    Explanations

    references to regulations and limitations that affect funding and insurance policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bearings
    -0.15
    935
    -0.14
    ören
    -0.14
    623
    -0.14
     footing
    -0.13
    783
    -0.13
    onet
    -0.13
     knight
    -0.13
    CTX
    -0.13
    604
    -0.13
    POSITIVE LOGITS
     limit
    0.75
     limits
    0.71
     cap
    0.67
     caps
    0.64
     Limits
    0.63
    limit
    0.62
     Limit
    0.61
     limitation
    0.59
    Limit
    0.58
     LIMIT
    0.57
    Act Density 0.325%

    No Known Activations