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

    Neuronpedia

    INDEX
    Explanations

    references to transportation or vehicles, particularly streetcars and trolleys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    trolley, car, or dolly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.39
    !
    -0.39
     Fink
    -0.37
    *
    -0.37
    <blockquote>
    -0.35
    ...
    -0.35
     
    -0.35
     in
    -0.35
    </blockquote>
    -0.34
    -
    -0.34
    POSITIVE LOGITS
     trolley
    2.20
     Trolley
    2.11
    rolley
    1.55
     trol
    1.43
     müſſen
    1.05
    ロウィン
    0.98
     laſſen
    0.93
     ainfi
    0.91
    <unused23>
    0.89
    majánló
    0.89
    Act Density 0.003%

    No Known Activations