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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating existence or presence, particularly through the use of the verb "is" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     symmetries
    -0.89
     contradictions
    -0.89
     flashbacks
    -0.89
     embodiments
    -0.87
     stereotypes
    -0.86
     markers
    -0.86
     clichés
    -0.85
     nightmares
    -0.84
     excuses
    -0.84
     arguments
    -0.84
    POSITIVE LOGITS
     lèvres
    0.67
     gouvernements
    0.67
     stuff
    0.67
     Stuff
    0.61
     legislation
    0.60
     vœux
    0.60
     oreilles
    0.59
     épaules
    0.58
     genoux
    0.58
     STUFF
    0.58
    Act Density 0.697%

    No Known Activations