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

    Neuronpedia

    INDEX
    Explanations

    phrases related to allegations of guilt and societal blame

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

    slaves and oppression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.91
     AssemblyCulture
    -0.42
     ģ
    -0.40
    IsMutable
    -0.40
     övers
    -0.40
    Geplaatst
    -0.40
    Życiorys
    -0.40
     deberes
    -0.39
     satisfactor
    -0.38
     neceff
    -0.37
    POSITIVE LOGITS
     transférez
    0.47
     '{@
    0.47
    setContentView
    0.43
    DeleteMapping
    0.42
     sweating
    0.39
    listFiles
    0.38
    CodeAttribute
    0.38
    ItemBackground
    0.38
     burning
    0.37
     supposedly
    0.37
    Act Density 0.091%

    No Known Activations