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

    Neuronpedia

    INDEX
    Explanations

    pronouns and demonstrative adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aget
    -0.15
    silver
    -0.14
     lawful
    -0.14
    ifact
    -0.14
     shiny
    -0.14
    ussy
    -0.14
    osh
    -0.13
    full
    -0.13
    ĥ
    -0.13
     Answers
    -0.13
    POSITIVE LOGITS
    zelf
    0.17
    agma
    0.16
    ViewState
    0.15
    abela
    0.15
    ayah
    0.15
    elop
    0.14
    UIFont
    0.14
    andel
    0.14
    arness
    0.14
    erver
    0.14
    Act Density 0.011%

    No Known Activations