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

    Neuronpedia

    INDEX
    Explanations

    phrases related to increases and decreases in various measurements

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

    increase in/of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.84
    tagHelperRunner
    -0.81
     للمعارف
    -0.81
     @"/
    -0.79
    Tembelea
    -0.75
     ſche
    -0.73
    :✨
    -0.72
    ніципалі
    -0.72
    IUrlHelper
    -0.72
    VYMaps
    -0.70
    POSITIVE LOGITS
     increasing
    0.49
    Increasing
    0.40
     Increasing
    0.40
     increase
    0.37
    increasing
    0.36
     increases
    0.35
     increased
    0.35
     zvyš
    0.34
     helg
    0.34
     zuneh
    0.33
    Act Density 0.127%

    No Known Activations