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

    Neuronpedia

    INDEX
    Explanations

    terms related to changes in numerical values or economic indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sÃłng
    -0.17
    utsch
    -0.16
    eniz
    -0.15
    lesh
    -0.15
    807
    -0.14
    abee
    -0.14
    ntag
    -0.14
     shemale
    -0.14
    uby
    -0.14
    ADED
    -0.14
    POSITIVE LOGITS
    nard
    0.15
     Underground
    0.14
    ohn
    0.14
    غاÙĦ
    0.14
     ed
    0.14
     Quar
    0.13
    rift
    0.13
    rack
    0.13
    lemen
    0.13
    инов
    0.13
    Act Density 0.046%

    No Known Activations