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

    Neuronpedia

    INDEX
    Explanations

    references to dolls and related items

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

    doll clothes and accessories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grünen
    -0.49
     McIntyre
    -0.46
     Gottfried
    -0.46
     Galbraith
    -0.44
     Weldon
    -0.44
    Rodney
    -0.44
    Brendan
    -0.43
    Gerhard
    -0.42
     homophobic
    -0.42
     Whitaker
    -0.41
    POSITIVE LOGITS
     doll
    1.98
     Doll
    1.95
     dolls
    1.78
    doll
    1.77
    Doll
    1.77
     Dolls
    1.68
     DOLL
    1.50
     boneca
    1.30
     poupée
    1.23
     muñeca
    1.13
    Act Density 0.006%

    No Known Activations