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

    Neuronpedia

    INDEX
    Explanations

    instances of discrimination or unequal treatment based on personal characteristics

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

    Pronouns followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    actors and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.72
     ويكيميديا
    -0.65
    ghijklmnop
    -0.65
    MeasureSpec
    -0.64
     tslint
    -0.64
    labelledby
    -0.64
    ifrance
    -0.61
    Према
    -0.61
     utafitiHapana
    -0.60
    těte
    -0.59
    POSITIVE LOGITS
     dared
    0.72
     dares
    0.61
     too
    0.60
     allegedly
    0.59
     dare
    0.58
    Too
    0.57
     Too
    0.56
     perceived
    0.53
    too
    0.53
     supposedly
    0.52
    Act Density 0.489%

    No Known Activations