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

    Neuronpedia

    INDEX
    Explanations

    references to racial discrimination and its impact

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

    Tokens preceding a verb

    np_acts-logits-general · gemini-2.0-flash

    supposed or alleged actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.60
    ValueGeneration
    -0.53
    sistency
    -0.53
    ])->
    -0.52
    '])->
    -0.52
     CreateTagHelper
    -0.51
    "]).
    -0.49
    ())).
    -0.49
    انجليز
    -0.49
    '))
    -0.48
    POSITIVE LOGITS
     somehow
    1.40
     яко
    1.35
     supposedly
    1.29
     supuestamente
    1.27
     allegedly
    1.06
     magically
    1.05
     angeb
    1.01
     Somehow
    0.94
    Somehow
    0.91
     supposed
    0.90
    Act Density 0.878%

    No Known Activations