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

    Neuronpedia

    INDEX
    Explanations

    long sentences containing the word "wrote"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wrote."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.80
    Unity
    -0.78
    Ĭ±
    -0.77
    agara
    -0.75
    phant
    -0.72
    angular
    -0.71
    illon
    -0.68
    nel
    -0.68
    ICES
    -0.66
    allows
    -0.65
    POSITIVE LOGITS
     letters
    0.91
     extensively
    0.83
     poems
    0.81
     eloqu
    0.81
     aloud
    0.80
     scathing
    0.79
     Letters
    0.79
     blog
    0.79
     sarcast
    0.77
     furiously
    0.76
    Act Density 0.043%

    No Known Activations