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

    Neuronpedia

    INDEX
    Explanations

    suffixes or word endings indicating various forms of names or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oday
    -0.16
     Ñģказ
    -0.15
    icago
    -0.15
    ingleton
    -0.15
    aux
    -0.15
    ãĥĥãĤ·ãĥ¥
    -0.15
    peak
    -0.14
     massa
    -0.13
     Trucks
    -0.13
    Curve
    -0.13
    POSITIVE LOGITS
     Medina
    0.15
    uster
    0.15
    ordinal
    0.14
     soon
    0.14
     closure
    0.14
    ýt
    0.14
     Nielsen
    0.14
    hetto
    0.14
    оÑĢдин
    0.13
     зада
    0.13
    Act Density 0.115%

    No Known Activations