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

    Neuronpedia

    INDEX
    Explanations

    terms related to rules, standards, and changes within structured systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mant
    -0.15
    mant
    -0.15
    peq
    -0.14
    pcf
    -0.14
    ilities
    -0.14
    deen
    -0.14
     Muss
    -0.14
     thanh
    -0.13
    las
    -0.13
    Assets
    -0.13
    POSITIVE LOGITS
    erner
    0.16
    Ñij
    0.16
    orte
    0.15
     choice
    0.15
    .cn
    0.14
     shapes
    0.14
     directions
    0.14
     ëĦ¤ìĿ´íĬ¸
    0.14
    oka
    0.14
    çĶ£
    0.14
    Act Density 0.062%

    No Known Activations