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

    Neuronpedia

    INDEX
    Explanations

    links to share articles or stories

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bats
    -0.78
     showers
    -0.66
     successors
    -0.65
    quartered
    -0.63
     ceilings
    -0.63
    amples
    -0.60
     Cutler
    -0.60
    storms
    -0.60
    iations
    -0.60
     roots
    -0.60
    POSITIVE LOGITS
     ARTICLE
    1.04
     article
    1.03
     guiActiveUn
    0.83
     week
    0.77
     story
    0.76
     month
    0.75
     page
    0.75
     blog
    0.75
    article
    0.73
     topic
    0.70
    Act Density 0.051%

    No Known Activations