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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wrote" indicating authorship or creating written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agara
    -0.73
    angular
    -0.72
    omical
    -0.69
    abol
    -0.68
    ĪĴ
    -0.67
    acles
    -0.67
     ILCS
    -0.67
    phant
    -0.67
    obyl
    -0.66
    nostic
    -0.65
    POSITIVE LOGITS
     sarcast
    0.90
     eloqu
    0.79
     rhet
    0.78
     letters
    0.75
     letter
    0.74
     wrote
    0.72
     scathing
    0.72
     quoting
    0.72
     furiously
    0.71
     caption
    0.70
    Act Density 0.019%

    No Known Activations