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

    Neuronpedia

    INDEX
    Explanations

    references to various types of schemes and structured plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ship
    -0.19
    خاÙĨÙĩ
    -0.17
    ried
    -0.16
    lier
    -0.15
    most
    -0.15
    sure
    -0.15
    anca
    -0.15
    unca
    -0.15
     McCabe
    -0.15
     McCart
    -0.15
    POSITIVE LOGITS
    atics
    0.22
    atically
    0.21
    antics
    0.21
    pered
    0.20
    ek
    0.19
    atic
    0.19
    forth
    0.17
    -wide
    0.16
    _FORE
    0.15
    pps
    0.15
    Act Density 0.015%

    No Known Activations