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

    Neuronpedia

    INDEX
    Explanations

    references to images or pictures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unate
    -0.16
    lest
    -0.15
    olk
    -0.15
    ctal
    -0.15
    *pow
    -0.14
    çıł
    -0.14
     impressions
    -0.14
    sworth
    -0.14
    -tm
    -0.14
    .hasMore
    -0.14
    POSITIVE LOGITS
    .twitter
    0.37
     tw
    0.21
     twitter
    0.20
     Tw
    0.20
    Twitter
    0.20
     Twitter
    0.20
    urious
    0.17
     twe
    0.17
    twitter
    0.17
    Tw
    0.17
    Act Density 0.002%

    No Known Activations