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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numerical patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    contres
    -0.15
    opis
    -0.15
    pron
    -0.14
    wor
    -0.14
    nze
    -0.14
    AndUpdate
    -0.13
    swer
    -0.13
    W
    -0.13
    iband
    -0.13
    ycin
    -0.12
    POSITIVE LOGITS
    аниÑĨ
    0.15
    isd
    0.14
    uma
    0.14
    igner
    0.14
    одÑĭ
    0.13
    eton
    0.13
    ulty
    0.13
    odom
    0.13
    ìµľê³ł
    0.13
    LinkId
    0.13
    Act Density 0.111%

    No Known Activations