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

    Neuronpedia

    INDEX
    Explanations

    phrases that specify the presence of "in" or contextual relationships within a larger discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergy
    -0.15
    cket
    -0.15
    اÙĨÙĪ
    -0.14
    ocket
    -0.14
    VISIBLE
    -0.14
    nvarchar
    -0.14
    lain
    -0.14
    /REC
    -0.14
    utes
    -0.14
    adj
    -0.14
    POSITIVE LOGITS
    orne
    0.15
     Prism
    0.15
    lick
    0.15
    ardi
    0.14
    licht
    0.14
    raw
    0.13
    990
    0.13
    olle
    0.13
    then
    0.13
     Humph
    0.13
    Act Density 0.276%

    No Known Activations