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

    Neuronpedia

    INDEX
    Explanations

    the action of posting content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "posting."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.75
     Brill
    -0.74
     Galile
    -0.70
    isin
    -0.69
    aila
    -0.69
    estial
    -0.68
     Sco
    -0.67
    vette
    -0.64
    apy
    -0.64
     Guerrero
    -0.64
    POSITIVE LOGITS
     posts
    1.00
     postings
    0.91
    ulate
    0.88
     posting
    0.83
     anonymously
    0.78
    post
    0.78
    aptic
    0.78
    pole
    0.76
    posted
    0.75
     submissions
    0.74
    Act Density 0.010%

    No Known Activations