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

    Neuronpedia

    INDEX
    Explanations

    authors of various written works

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating authorship and the number of works by different authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.71
    MSN
    -0.65
     Fuj
    -0.62
     magnification
    -0.60
     grouping
    -0.60
     broom
    -0.60
     camer
    -0.58
    pring
    -0.58
     loosen
    -0.57
     limitation
    -0.57
    POSITIVE LOGITS
    itatively
    0.79
     books
    0.77
    letters
    0.75
     memoir
    0.74
     Awakens
    0.73
     blogs
    0.71
     Surv
    0.69
     novels
    0.68
     essays
    0.67
     poems
    0.66
    Act Density 0.072%

    No Known Activations