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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns and adjectives

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

    Este esse essa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.56
     Jiao
    -0.52
     BrowserModule
    -0.51
    atino
    -0.50
    PreferredItem
    -0.50
    aros
    -0.49
     Roost
    -0.49
    Ramos
    -0.49
    客様
    -0.48
     linho
    -0.47
    POSITIVE LOGITS
    Esse
    0.84
     Esse
    0.84
     Essa
    0.79
     esse
    0.78
    Essa
    0.78
     essa
    0.75
     desse
    0.75
     nessa
    0.71
     dessa
    0.65
     dessas
    0.61
    Act Density 0.003%

    No Known Activations