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

    Neuronpedia

    INDEX
    Explanations

    references to toilets and related hygiene items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uesia
    -0.75
    sidemargin
    -0.73
    Ligações
    -0.72
    +#+
    -0.71
     enfance
    -0.70
     Flav
    -0.66
    Flav
    -0.65
     CORD
    -0.65
    ỡng
    -0.63
     Spraw
    -0.63
    POSITIVE LOGITS
     toilet
    2.84
     toilets
    2.49
    toilet
    2.44
     Toilet
    2.41
    Toilet
    2.34
    ilets
    1.71
     toilettes
    1.39
     туа
    1.37
     toilette
    1.36
    toile
    1.35
    Act Density 0.090%

    No Known Activations