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

    Neuronpedia

    INDEX
    Explanations

    sentences that emphasize the importance or impact of a particular person or action

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express conclusive statements or remarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encl
    -0.89
     autonom
    -0.86
     authorised
    -0.80
     censored
    -0.79
     enclosed
    -0.77
     vegetarian
    -0.76
    riet
    -0.76
     behaviour
    -0.75
     anthrop
    -0.75
     compulsory
    -0.74
    POSITIVE LOGITS
     Granted
    1.38
     Regardless
    1.22
     Considering
    1.17
     Hopefully
    1.15
     Especially
    1.15
     Expect
    1.14
     Additionally
    1.13
     Obviously
    1.12
     Unfortunately
    1.11
     Conversely
    1.10
    Act Density 0.366%

    No Known Activations