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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proximity or nearness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.18
    енко
    -0.16
    ulong
    -0.16
    edb
    -0.16
    edo
    -0.15
    urator
    -0.15
    gan
    -0.15
    gregator
    -0.15
    моÑĤÑĢеÑĤÑĮ
    -0.15
    eff
    -0.15
    POSITIVE LOGITS
    ness
    0.27
    shore
    0.27
    ctic
    0.26
    abouts
    0.26
     misses
    0.25
    by
    0.25
     Äijây
    0.24
    lier
    0.24
    s
    0.24
    -term
    0.24
    Act Density 0.028%

    No Known Activations