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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate frequency or quantity in relation to groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uck
    -0.17
     سÙħ
    -0.15
    gtk
    -0.15
    ův
    -0.14
    Æ¡
    -0.14
     overd
    -0.13
    esar
    -0.13
    apo
    -0.13
    thus
    -0.13
    iram
    -0.13
    POSITIVE LOGITS
     which
    0.28
     them
    0.23
     whose
    0.23
     whom
    0.22
     коÑĤоÑĢой
    0.19
     cuales
    0.18
     коÑĤоÑĢÑĭÑħ
    0.18
    which
    0.17
     Which
    0.16
     Lev
    0.16
    Act Density 0.018%

    No Known Activations