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

    Neuronpedia

    INDEX
    Explanations

    references to trains or railroad-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assy
    -0.17
    ritis
    -0.17
    ting
    -0.16
    itzer
    -0.16
    ing
    -0.16
    adder
    -0.14
    uppy
    -0.14
    ADE
    -0.14
    instein
    -0.14
    plier
    -0.14
    POSITIVE LOGITS
    ees
    0.28
    ee
    0.21
    loads
    0.19
    /bus
    0.19
    ings
    0.19
     station
    0.18
    load
    0.17
     derail
    0.17
    buff
    0.17
    bart
    0.17
    Act Density 0.011%

    No Known Activations