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

    Neuronpedia

    INDEX
    Explanations

    references to plans or organized efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ship
    -0.21
    خاÙĨÙĩ
    -0.18
     McCabe
    -0.17
     McCart
    -0.16
    rome
    -0.16
    most
    -0.16
    lene
    -0.15
    shr
    -0.15
    ÑģÑİ
    -0.15
    qui
    -0.15
    POSITIVE LOGITS
    atics
    0.24
    pered
    0.22
    atically
    0.22
    antics
    0.21
    atic
    0.20
    pering
    0.17
    forth
    0.17
    atical
    0.17
    yard
    0.17
    pton
    0.17
    Act Density 0.015%

    No Known Activations