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

    Neuronpedia

    INDEX
    Explanations

    terms related to gaining or obtaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.16
    ials
    -0.16
     times
    -0.15
     icing
    -0.15
    times
    -0.15
     danger
    -0.14
    ãĥ¼ãĥį
    -0.14
    venir
    -0.14
    al
    -0.14
    go
    -0.13
    POSITIVE LOGITS
     traction
    0.29
     momentum
    0.26
    /loose
    0.23
    fully
    0.22
     footing
    0.21
    bourg
    0.20
     ground
    0.19
     insight
    0.19
     Momentum
    0.19
     footh
    0.19
    Act Density 0.023%

    No Known Activations