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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases that imply negativity or criticism

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

    gadgets, thingies, and wacky terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bkz
    -0.43
     kasarigan
    -0.43
    Referințe
    -0.39
    droje
    -0.37
     Stellung
    -0.37
    ikbaar
    -0.35
     referrerpolicy
    -0.34
     "..\..\
    -0.33
     فريبيس
    -0.33
     fordern
    -0.33
    POSITIVE LOGITS
     Réponses
    0.68
     giz
    0.68
     thingy
    0.64
     wacky
    0.63
     gadget
    0.60
     Baz
    0.60
     gadgets
    0.59
     shenanigans
    0.58
     widgets
    0.57
     Giz
    0.57
    Act Density 0.047%

    No Known Activations