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

    Neuronpedia

    INDEX
    Explanations

    determiners and adjectives that indicate quantity or valuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OMEM
    -0.18
    fet
    -0.16
    vik
    -0.16
    oke
    -0.15
    alle
    -0.14
    éģ¸æīĭ
    -0.14
    ayi
    -0.14
    pawn
    -0.13
    ulus
    -0.13
     Counts
    -0.13
    POSITIVE LOGITS
     mere
    0.19
    mere
    0.18
    aghan
    0.16
     whopping
    0.16
    403
    0.16
    alsy
    0.15
     meas
    0.15
     trium
    0.15
     thr
    0.15
    zy
    0.14
    Act Density 0.067%

    No Known Activations