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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing or expressing the significance or impact of something

    oai_token-act-pair · gpt-3.5-turbo

    statements or phrases related to the state of being, particularly with the verb "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.72
     sidx
    -0.70
    LLOW
    -0.70
     Discuss
    -0.69
    udeau
    -0.68
    è¦ļéĨĴ
    -0.68
    untled
    -0.68
    byss
    -0.68
     Cosponsors
    -0.66
     accuses
    -0.66
    POSITIVE LOGITS
     gonna
    1.52
     definitely
    1.21
     really
    1.20
     unbelievable
    1.19
     gotta
    1.15
     kinda
    1.14
     basically
    1.12
     phenomenal
    1.10
     obviously
    1.10
     amazing
    1.09
    Act Density 0.247%

    No Known Activations