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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their contents in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anja
    -0.14
    inary
    -0.13
    undo
    -0.13
    oord
    -0.13
    å¹ħ
    -0.13
    avras
    -0.13
    ingu
    -0.13
    رÙĬÙĤ
    -0.13
     Resident
    -0.12
    tru
    -0.12
    POSITIVE LOGITS
     whose
    0.18
     see
    0.15
     which
    0.15
    whose
    0.15
     cui
    0.15
    pictured
    0.15
     www
    0.15
    PLICIT
    0.15
    λλι
    0.14
     motto
    0.14
    Act Density 0.119%

    No Known Activations