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

    Neuronpedia

    INDEX
    Explanations

    references to historical transportation artifacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iteli
    -0.17
    icode
    -0.15
    estring
    -0.15
    nano
    -0.15
    lian
    -0.14
    xea
    -0.14
    core
    -0.14
    .gdx
    -0.14
    ilib
    -0.14
     frankfurt
    -0.14
    POSITIVE LOGITS
     steam
    0.22
     Steam
    0.21
     boiler
    0.20
     Boiler
    0.19
     Class
    0.19
     boilers
    0.18
     locom
    0.18
    steam
    0.17
    Steam
    0.17
    usterity
    0.17
    Act Density 0.010%

    No Known Activations