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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or requests

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a strong conclusive or final thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lled
    -0.78
    lier
    -0.72
     quir
    -0.72
     poked
    -0.69
     underwater
    -0.69
     submerged
    -0.68
     lizard
    -0.68
     unlucky
    -0.68
     cavern
    -0.67
     bas
    -0.67
    POSITIVE LOGITS
     Therefore
    1.23
     Additionally
    1.15
     Unfortunately
    1.15
     Such
    1.14
     Ultimately
    1.12
     However
    1.09
     Accordingly
    1.07
     Sadly
    1.06
     Furthermore
    1.06
     Moreover
    1.04
    Act Density 0.665%

    No Known Activations