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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce lists or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORB
    -0.16
    lya
    -0.15
     Mug
    -0.15
    μαν
    -0.15
    inski
    -0.14
    rocket
    -0.14
    BOSE
    -0.14
     repeat
    -0.14
    hs
    -0.14
     æł
    -0.14
    POSITIVE LOGITS
    uten
    0.18
    untas
    0.16
    ujet
    0.15
    wner
    0.15
    ÅŁehir
    0.15
    plet
    0.15
    plen
    0.15
     cam
    0.14
    quer
    0.14
    VERTISE
    0.14
    Act Density 0.032%

    No Known Activations