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

    Neuronpedia

    INDEX
    Explanations

    references to trains and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itzer
    -0.18
    plier
    -0.17
     Airlines
    -0.17
    enger
    -0.17
    assy
    -0.16
    ophon
    -0.16
    ents
    -0.15
    214
    -0.15
    aurus
    -0.15
    ipers
    -0.14
    POSITIVE LOGITS
    ees
    0.33
    ee
    0.27
    ings
    0.23
    loads
    0.20
    /bus
    0.18
    load
    0.17
    bow
    0.16
     robber
    0.16
    bows
    0.16
     tượng
    0.16
    Act Density 0.011%

    No Known Activations