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

    Neuronpedia

    INDEX
    Explanations

    words indicating quantity or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nÃło
    -0.18
     certain
    -0.17
    editary
    -0.15
     Certain
    -0.14
    swire
    -0.14
    izia
    -0.14
    _stuff
    -0.14
    ÙĩاÛĮ
    -0.14
     vÃłi
    -0.13
    IENCE
    -0.13
    POSITIVE LOGITS
     sclerosis
    0.23
     times
    0.18
    clerosis
    0.17
    -many
    0.17
    次
    0.16
    elper
    0.15
    -layer
    0.15
    ely
    0.15
     ways
    0.15
    ness
    0.14
    Act Density 0.032%

    No Known Activations