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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and patterns within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilo
    -0.16
    ÑģÑİ
    -0.15
    hf
    -0.15
    ilation
    -0.15
    rán
    -0.14
    pak
    -0.14
    äºŃ
    -0.14
    inv
    -0.14
    ral
    -0.14
     coal
    -0.13
    POSITIVE LOGITS
    affles
    0.14
    orning
    0.14
    appers
    0.14
     Bender
    0.13
     appart
    0.13
    ее
    0.13
     лÑİ
    0.13
    tainment
    0.13
     uncon
    0.13
     Scre
    0.13
    Act Density 0.053%

    No Known Activations