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

    Neuronpedia

    INDEX
    Explanations

    terms related to subway systems and transportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewe
    -0.19
    .Aggressive
    -0.15
    'gc
    -0.14
    isci
    -0.14
    _grade
    -0.14
     tracks
    -0.14
     grade
    -0.14
    iq
    -0.14
    agua
    -0.14
    Grade
    -0.14
    POSITIVE LOGITS
     cars
    0.35
     car
    0.31
     coaches
    0.30
     coach
    0.28
     Cars
    0.26
    cars
    0.26
     Pull
    0.25
    Cars
    0.25
     bog
    0.23
    coach
    0.23
    Act Density 0.010%

    No Known Activations