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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'Tak' followed by a sequence of alphanumeric characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Tak" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.82
     livest
    -0.80
    ORPG
    -0.79
     DRAG
    -0.77
    anwhile
    -0.68
    pherd
    -0.66
     Grind
    -0.63
     reception
    -0.62
     obser
    -0.62
     guiActiveUnfocused
    -0.62
    POSITIVE LOGITS
    amaru
    1.10
    istani
    1.06
    atsuki
    1.01
     Tak
    1.00
    umar
    0.99
    ota
    0.99
    uba
    0.97
    iba
    0.92
    ushi
    0.91
    kun
    0.91
    Act Density 0.013%

    No Known Activations