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

    Neuronpedia

    INDEX
    Explanations

    references to railway infrastructure and transportation systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    966
    -0.15
    rito
    -0.15
     Pipes
    -0.15
     Roads
    -0.14
    178
    -0.14
    ëĤ
    -0.14
    Å¡ka
    -0.14
    åĦ
    -0.13
    _entropy
    -0.13
    rots
    -0.13
    POSITIVE LOGITS
     train
    0.48
     Train
    0.46
     trains
    0.45
    Train
    0.42
    train
    0.38
    .train
    0.35
     rail
    0.34
     Rail
    0.34
    _train
    0.34
    (train
    0.33
    Act Density 0.233%

    No Known Activations