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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns or phrases indicating specific objects or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eward
    -0.16
    nj
    -0.15
    imer
    -0.15
    ãĥ¬ãĥ³
    -0.14
    history
    -0.14
    stag
    -0.14
    θα
    -0.14
    StackNavigator
    -0.14
    ham
    -0.14
     заÑħод
    -0.14
    POSITIVE LOGITS
    eldo
    0.16
    ìĦŃ
    0.14
    ož
    0.14
    BoxLayout
    0.14
    eria
    0.14
    eza
    0.14
    侯
    0.14
    vana
    0.13
    paged
    0.13
     VERSION
    0.13
    Act Density 0.107%

    No Known Activations