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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the word 'single'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alon
    -0.21
    ulace
    -0.17
    azz
    -0.15
    ceu
    -0.15
    inspace
    -0.15
    ë¦Ħ
    -0.15
    ãĥ¼ãĤ¸
    -0.15
    []={
    -0.15
    cht
    -0.15
    meer
    -0.15
    POSITIVE LOGITS
    RIX
    0.15
     alike
    0.15
    igned
    0.14
     Architect
    0.14
    iferay
    0.14
    tras
    0.14
    ruta
    0.13
     Trafford
    0.13
    ruc
    0.13
    erton
    0.13
    Act Density 0.012%

    No Known Activations