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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parentheses and related punctuation in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erten
    -0.17
    elter
    -0.15
    hai
    -0.15
    aturas
    -0.15
    nia
    -0.14
    ãĤ·ãĤ¢
    -0.14
    ekten
    -0.14
    elts
    -0.14
    ungs
    -0.14
     ↵↵
    -0.14
    POSITIVE LOGITS
    ÑĢÑĮ
    0.16
    missive
    0.15
    ulla
    0.14
    mere
    0.14
    YLE
    0.14
    uli
    0.14
    ieme
    0.14
    .hxx
    0.14
    åħĪ
    0.14
    _verbose
    0.13
    Act Density 0.044%

    No Known Activations