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

    Neuronpedia

    INDEX
    Explanations

    the end of a sentence or phrase with emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statements that indicate significant events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omics
    -0.82
     ageing
    -0.73
     invincible
    -0.68
    ikuman
    -0.68
     nature
    -0.67
     tyr
    -0.65
     status
    -0.65
     independ
    -0.65
    eme
    -0.64
     properties
    -0.63
    POSITIVE LOGITS
     Instead
    1.17
     Similarly
    1.15
     Moreover
    1.14
     Nonetheless
    1.14
     Likewise
    1.13
     Additionally
    1.13
     Indeed
    1.11
     Fortunately
    1.09
     Nevertheless
    1.09
     However
    1.07
    Act Density 0.752%

    No Known Activations