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

    Neuronpedia

    INDEX
    Explanations

    recurring symbols or repetitions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icht
    -0.17
    agma
    -0.16
    ersist
    -0.15
    caff
    -0.14
    eye
    -0.14
    endency
    -0.14
    ecta
    -0.14
    dech
    -0.14
    egr
    -0.14
    ounded
    -0.14
    POSITIVE LOGITS
    ull
    0.18
    adr
    0.18
    iem
    0.18
    rum
    0.17
    rest
    0.17
    ras
    0.17
    ÑĢаÑĤ
    0.17
     ÑĤомÑĥ
    0.17
    ac
    0.17
    иÑĤай
    0.17
    Act Density 0.008%

    No Known Activations