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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotes and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĩÙĦ
    -0.17
    rights
    -0.17
    å¹¹
    -0.14
    selling
    -0.14
    lear
    -0.14
    noun
    -0.14
    reve
    -0.14
     !***
    -0.14
    çīĮ
    -0.14
    votes
    -0.14
    POSITIVE LOGITS
    s
    0.21
    de
    0.21
    od
    0.20
    als
    0.20
    ese
    0.19
    anges
    0.19
    dy
    0.19
    ok
    0.19
    ses
    0.18
    be
    0.18
    Act Density 0.040%

    No Known Activations