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

    Neuronpedia

    INDEX
    Explanations

    pronouns and forms of the verb "to be" in various contexts

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

    after pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ObservableList
    -0.39
    BindView
    -0.39
     bod
    -0.31
     situation
    -0.31
    therefore
    -0.31
     therefore
    -0.30
    force
    -0.30
     préf
    -0.30
    niów
    -0.29
    expect
    -0.29
    POSITIVE LOGITS
     nadat
    0.86
     nachdem
    0.86
     after
    0.81
    after
    0.78
     після
    0.77
     After
    0.77
    \{\\
    0.75
    katapos
    0.75
     después
    0.74
     после
    0.74
    Act Density 0.010%

    No Known Activations