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

    Neuronpedia

    INDEX
    Explanations

    statistics and results in baseball games

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

    followed by a preposition or punctuation

    np_acts-logits-general · gemini-2.0-flash

    strike or retire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.62
     Chwiliwch
    -0.61
    +#+#
    -0.60
    #+#
    -0.58
    RenderAtEndOf
    -0.57
    SizeMode
    -0.57
    RTEX
    -0.55
     ***!
    -0.55
     CreateTagHelper
    -0.55
    ędzynarod
    -0.54
    POSITIVE LOGITS
     striking
    0.94
     struck
    0.85
     strike
    0.79
     retiring
    0.74
     Striking
    0.74
     retired
    0.72
     retire
    0.70
     Strike
    0.70
    struck
    0.68
    Strike
    0.67
    Act Density 0.149%

    No Known Activations