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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their relative frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iet
    -0.20
    hausen
    -0.16
    dba
    -0.16
    ling
    -0.15
    idge
    -0.14
    ity
    -0.14
     liebe
    -0.14
     hostage
    -0.14
     Ary
    -0.14
     t
    -0.14
    POSITIVE LOGITS
    izmet
    0.15
     moden
    0.15
    assin
    0.15
    DMI
    0.15
    olson
    0.14
    ToBounds
    0.14
    ÙĬÙģ
    0.14
    оже
    0.14
    vise
    0.14
     ÐĹаÑħ
    0.14
    Act Density 0.014%

    No Known Activations