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

    Neuronpedia

    INDEX
    Explanations

    phrases that encourage open communication or offer help

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

    offers to interact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.52
     HttpNotFound
    -0.51
    setVerticalGroup
    -0.51
    AndEndTag
    -0.47
    IntoConstraints
    -0.46
    NTSTATUS
    -0.46
    verifyException
    -0.46
    లాలు
    -0.46
     EClass
    -0.46
    $_['
    -0.45
    POSITIVE LOGITS
     kindly
    0.54
     Anytime
    0.52
     forgive
    0.51
     οπο
    0.51
     please
    0.51
    随意
    0.50
     Feel
    0.49
     spare
    0.49
     enjoy
    0.49
     bebas
    0.49
    Act Density 0.003%

    No Known Activations