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

    Neuronpedia

    INDEX
    Explanations

    significant words or phrases that denote identity or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gis
    -0.17
    egal
    -0.15
    彦
    -0.15
     詳細
    -0.15
    urga
    -0.15
    ç´§
    -0.14
    chine
    -0.14
    antis
    -0.14
    obo
    -0.14
    à¸Ńà¸ģà¸Īาà¸ģ
    -0.14
    POSITIVE LOGITS
     gradually
    0.18
     behind
    0.17
     part
    0.17
     gradual
    0.15
     our
    0.15
    å¾IJ
    0.15
    asa
    0.15
     according
    0.15
     underlying
    0.15
     increment
    0.14
    Act Density 0.005%

    No Known Activations