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

    Neuronpedia

    INDEX
    Explanations

    references to the word "one" or variations of it

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

    Following "one"

    np_acts-logits-general · gemini-2.0-flash

    single instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saites
    -0.86
     Roskov
    -0.80
     dialects
    -0.73
    tagHelperRunner
    -0.70
     equivalents
    -0.69
     ſche
    -0.69
     orbitals
    -0.67
    Personensuche
    -0.65
     subsidies
    -0.64
     raiſ
    -0.64
    POSITIVE LOGITS
     thing
    0.96
     person
    0.87
     pair
    0.71
     pouvoirs
    0.69
     instance
    0.69
     place
    0.68
     large
    0.66
     attentes
    0.65
    thing
    0.62
     big
    0.61
    Act Density 0.188%

    No Known Activations