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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "wrote"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "wrote"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illon
    -0.76
    angular
    -0.75
    Unity
    -0.75
    Ĭ±
    -0.74
    agara
    -0.72
     ILCS
    -0.70
    negie
    -0.69
    phant
    -0.69
    ĪĴ
    -0.68
    icons
    -0.68
    POSITIVE LOGITS
     letters
    0.83
     eloqu
    0.80
     furiously
    0.80
     penned
    0.76
     extensively
    0.76
     separately
    0.76
     sarcast
    0.75
     memos
    0.74
     scathing
    0.74
     aloud
    0.70
    Act Density 0.040%

    No Known Activations