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

    Neuronpedia

    INDEX
    Explanations

    frequent decimal numbers or numerical patterns within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    846
    -0.15
     Leban
    -0.15
    agt
    -0.15
    ää
    -0.15
     seedu
    -0.14
    okud
    -0.14
     adv
    -0.14
    ijkstra
    -0.14
    eno
    -0.13
    ateg
    -0.13
    POSITIVE LOGITS
    iyel
    0.16
    azen
    0.16
    ków
    0.15
    âĢį
    0.14
    경기
    0.14
    orch
    0.13
    zac
    0.13
    rometer
    0.13
    rx
    0.13
    .rnn
    0.13
    Act Density 0.038%

    No Known Activations