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

    Neuronpedia

    INDEX
    Explanations

    instances of terms related to removal or exclusion

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

    removing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.85
    webElementXpaths
    -0.70
    +#+#
    -0.66
     Ballad
    -0.65
    RenderAtEndOf
    -0.64
    HostException
    -0.63
    urlpatterns
    -0.63
    ſchaft
    -0.61
    MessageTagHelper
    -0.61
    AndEndTag
    -0.60
    POSITIVE LOGITS
     removal
    0.92
     removed
    0.91
     remove
    0.90
     removing
    0.90
     Remove
    0.88
     Removal
    0.86
    Remove
    0.81
    Removing
    0.80
     Removing
    0.79
     removes
    0.78
    Act Density 0.021%

    No Known Activations