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

    Neuronpedia

    INDEX
    Explanations

    numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idi
    -1.62
    ridges
    -1.60
    eness
    -1.56
    fork
    -1.54
     upside
    -1.54
    river
    -1.47
     line
    -1.42
    éd
    -1.42
     tighter
    -1.40
    chain
    -1.40
    POSITIVE LOGITS
    00
    1.59
    cember
    1.52
    ffen
    1.50
    ophers
    1.44
    eland
    1.43
    venth
    1.42
    еÐ
    1.41
    adier
    1.39
     ratings
    1.38
    xture
    1.37
    Act Density 0.208%

    No Known Activations