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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and symbols used in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addir
    -0.16
    illage
    -0.15
    lick
    -0.15
    entials
    -0.15
    çĽijåIJ¬é¡µéĿ¢
    -0.14
    _-_
    -0.14
    êu
    -0.14
    kud
    -0.14
    eras
    -0.14
    'value
    -0.14
    POSITIVE LOGITS
    .nn
    0.14
     @}
    0.14
    TPL
    0.14
    PRINTF
    0.14
     raison
    0.14
    u
    0.14
     Trap
    0.13
     reason
    0.13
    agli
    0.13
    ucher
    0.13
    Act Density 0.065%

    No Known Activations