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

    Neuronpedia

    INDEX
    Explanations

    formatting and punctuation elements in numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hea
    -0.15
    ehler
    -0.15
    ostel
    -0.14
    ocha
    -0.14
    oca
    -0.14
     zw
    -0.14
    bero
    -0.14
    oper
    -0.14
    nech
    -0.14
    eca
    -0.14
    POSITIVE LOGITS
    zl
    0.17
     amp
    0.17
    azen
    0.16
    ÑĢел
    0.15
     Sig
    0.15
     intf
    0.14
     Bob
    0.14
     uk
    0.14
     de
    0.14
     Trap
    0.14
    Act Density 0.077%

    No Known Activations