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

    Neuronpedia

    INDEX
    Explanations

    numeric values or numerical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olar
    -0.17
    Ñģол
    -0.16
     Walt
    -0.16
    nonnull
    -0.15
    ermann
    -0.15
    nts
    -0.14
    خر
    -0.14
    ýn
    -0.14
     ем
    -0.14
    Ïĩε
    -0.14
    POSITIVE LOGITS
    zed
    0.16
    _contin
    0.15
    ISBN
    0.14
    isÃŃ
    0.14
    aroo
    0.14
     incon
    0.13
    ownik
    0.13
     arbit
    0.13
     anon
    0.13
    ceu
    0.13
    Act Density 0.006%

    No Known Activations