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

    Neuronpedia

    INDEX
    Explanations

    parentheses and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (),
    -0.08
    _)
    -0.07
    endoza
    -0.07
     _______,
    -0.07
     ...)
    -0.07
    _]
    -0.07
    jured
    -0.07
     *)
    -0.07
    *)
    -0.07
    áo
    -0.07
    POSITIVE LOGITS
    amil
    0.07
     Additionally
    0.07
    ndl
    0.06
    achten
    0.06
    ikh
    0.06
     ведÑĮ
    0.06
    aptcha
    0.06
     thereby
    0.06
     originals
    0.06
     note
    0.06
    Act Density 0.090%

    No Known Activations