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

    Neuronpedia

    INDEX
    Explanations

    contradictory conjunctions and transitions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilin
    -0.15
    sworth
    -0.15
    odÃŃ
    -0.15
    ignon
    -0.15
    strup
    -0.15
     fmap
    -0.15
    ipse
    -0.14
    ÑĢод
    -0.14
    instead
    -0.14
    vara
    -0.13
    POSITIVE LOGITS
    .land
    0.16
    ano
    0.15
    uml
    0.15
    ä»°
    0.14
    nels
    0.14
    ess
    0.14
    ëł
    0.13
    ANO
    0.13
    CHAN
    0.13
     Shank
    0.13
    Act Density 0.209%

    No Known Activations