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

    Neuronpedia

    INDEX
    Explanations

    words related to written articles and publications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "this article" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sed
    -0.73
    ibles
    -0.70
     Maid
    -0.69
    Ĭ±
    -0.68
    bats
    -0.65
     strang
    -0.64
     Surprise
    -0.64
     warranties
    -0.63
     Mouth
    -0.62
    sbm
    -0.61
    POSITIVE LOGITS
    gha
    0.75
    ilion
    0.71
    ittee
    0.68
     assumes
    0.68
     SHALL
    0.68
    ounce
    0.67
    ARE
    0.64
     adapted
    0.64
    REC
    0.63
    ebin
    0.62
    Act Density 0.084%

    No Known Activations