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

    Neuronpedia

    INDEX
    Explanations

    references to toys and toy-related concepts

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

    toy or toys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Burke
    -0.52
     Wellen
    -0.51
     Autorisations
    -0.48
     MDC
    -0.47
     Cummins
    -0.46
     médié
    -0.46
     Eriksson
    -0.45
    wellen
    -0.45
     Cronin
    -0.44
    ・)
    -0.44
    POSITIVE LOGITS
     toy
    2.34
    Toy
    2.27
     Toy
    2.25
    toy
    2.06
     TOY
    1.77
     toys
    1.76
    toys
    1.68
    TOY
    1.57
     jouet
    1.56
    Toys
    1.54
    Act Density 0.003%

    No Known Activations