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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases that suggest a transition or change in state or condition

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

    once followed by a clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     different
    -0.32
    esgue
    -0.32
    inflater
    -0.30
     heart
    -0.29
    allowNull
    -0.29
     various
    -0.29
     spek
    -0.29
    mActivity
    -0.28
     week
    -0.27
     differently
    -0.27
    POSITIVE LOGITS
    Once
    0.81
     Once
    0.76
     Sobald
    0.76
     nachdem
    0.71
     للاسماء
    0.69
    EndInit
    0.69
    ONCE
    0.68
     ONCE
    0.67
     Nachdem
    0.66
     sobald
    0.66
    Act Density 0.027%

    No Known Activations