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

    Neuronpedia

    INDEX
    Explanations

    references to formal institutions or authoritative sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favors
    -0.70
     isolato
    -0.67
    Rohy
    -0.65
     OSHA
    -0.64
     abstrait
    -0.63
     Lafayette
    -0.62
     îna
    -0.62
     Hiram
    -0.61
     ModelExpression
    -0.60
     exécu
    -0.60
    POSITIVE LOGITS
     realised
    1.32
    Whilst
    1.30
    behaviour
    1.29
     specialises
    1.28
    initialise
    1.28
     tyres
    1.27
     specialise
    1.26
     Whilst
    1.26
    Behaviour
    1.26
     realise
    1.25
    Act Density 1.696%

    No Known Activations