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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving polynomials and equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     slightly
    -0.08
    ,
    -0.07
     regular
    -0.07
    bett
    -0.06
     per
    -0.06
     simple
    -0.06
    erv
    -0.06
     during
    -0.06
     different
    -0.06
     best
    -0.06
    POSITIVE LOGITS
    åº
    0.08
    BOOLE
    0.07
    ewidth
    0.07
    ãĤ¤ãĤº
    0.07
     Ñģлож
    0.07
    _COMPLEX
    0.07
     ëį¤íĶĦ
    0.07
    _QMARK
    0.06
    اÙĬات
    0.06
    indre
    0.06
    Act Density 0.052%

    No Known Activations