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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating differing methods or practices, particularly in the context of comparisons and operational frameworks

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

    run with or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     huom
    -0.35
     henkil
    -0.32
     siir
    -0.32
     sisält
    -0.32
     mahdol
    -0.31
     väli
    -0.30
     nedeniyle
    -0.30
    ⓧ
    -0.30
     hänen
    -0.30
    uestas
    -0.29
    POSITIVE LOGITS
     run
    1.60
     running
    1.59
     Running
    1.56
     runs
    1.49
    Running
    1.48
     Runs
    1.48
    running
    1.48
     Run
    1.47
    Run
    1.45
     RUN
    1.42
    Act Density 0.048%

    No Known Activations