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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the publication of content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "published" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xa
    -0.76
    poke
    -0.73
    bones
    -0.73
    ugh
    -0.71
    FX
    -0.71
    aura
    -0.70
    enez
    -0.70
    mer
    -0.70
    phant
    -0.68
    Ĭ±
    -0.67
    POSITIVE LOGITS
    lishing
    1.15
     excerpts
    1.00
    lisher
    0.93
    lishes
    0.90
     anonymously
    0.85
     journals
    0.80
     journal
    0.79
     pamph
    0.78
     articles
    0.77
     publication
    0.74
    Act Density 0.060%

    No Known Activations