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

    Neuronpedia

    INDEX
    Explanations

    terms related to train stations and railways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     planned
    -0.14
     rupture
    -0.14
    opal
    -0.14
    793
    -0.13
     Berger
    -0.13
    illance
    -0.13
    redd
    -0.13
    dates
    -0.13
     metab
    -0.13
    ênh
    -0.13
    POSITIVE LOGITS
    Train
    0.17
     train
    0.17
    ASCII
    0.16
    chez
    0.15
     trains
    0.15
    allon
    0.15
     therap
    0.15
    åį·
    0.14
    train
    0.14
    .train
    0.14
    Act Density 0.171%

    No Known Activations