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

    Neuronpedia

    INDEX
    Explanations

    numeric and mathematical concepts, particularly those related to calculations and indices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eller
    -0.17
    ander
    -0.15
    nak
    -0.15
    atten
    -0.15
     bis
    -0.14
     carbon
    -0.14
    až
    -0.14
    .)↵↵↵↵
    -0.14
    opy
    -0.14
    otes
    -0.14
    POSITIVE LOGITS
    oso
    0.16
    onen
    0.14
     Tweet
    0.14
    ulled
    0.14
    stderr
    0.14
    ULA
    0.14
    بÙĪÙĦ
    0.13
    rov
    0.13
     Maxim
    0.13
     Exercise
    0.13
    Act Density 0.021%

    No Known Activations