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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negative aspects or disadvantages

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

    downside and upside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    versammlung
    -0.44
     bricks
    -0.41
     Bat
    -0.41
     correct
    -0.40
     conference
    -0.40
    //*[@
    -0.38
     المج
    -0.37
     toek
    -0.37
     break
    -0.37
     CreateTagHelper
    -0.37
    POSITIVE LOGITS
     downside
    1.45
     downsides
    1.16
     drawback
    0.71
     Nachteile
    0.71
    pshot
    0.71
     Wikiseite
    0.67
    MigrationBuilder
    0.67
     disadvantage
    0.67
     inconvénients
    0.66
     Upside
    0.65
    Act Density 0.005%

    No Known Activations