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

    Neuronpedia

    INDEX
    Explanations

    references to testing and engineering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    539
    -0.16
     pil
    -0.15
    Dispatch
    -0.15
    modifier
    -0.15
     Hanna
    -0.14
    avig
    -0.14
     سÙħ
    -0.14
    competitive
    -0.14
    195
    -0.14
     Lives
    -0.14
    POSITIVE LOGITS
     attitude
    0.23
     checkout
    0.19
     thr
    0.19
     umb
    0.18
     aft
    0.17
     commanded
    0.17
     Checkout
    0.17
     commanding
    0.17
    checkout
    0.17
     cry
    0.16
    Act Density 0.050%

    No Known Activations