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

    Neuronpedia

    INDEX
    Explanations

    architectural descriptors and features related to open spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hell
    -0.16
    .Glide
    -0.15
    925
    -0.15
    pon
    -0.15
    رة
    -0.15
    arin
    -0.14
    .failure
    -0.14
    indi
    -0.14
    ograd
    -0.14
    سÙĥ
    -0.14
    POSITIVE LOGITS
    mant
    0.18
    ôi
    0.16
    itemid
    0.15
    ameleon
    0.15
    iff
    0.15
    atham
    0.15
    uffle
    0.15
    veau
    0.15
     Wood
    0.15
    _rb
    0.14
    Act Density 0.022%

    No Known Activations