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

    Neuronpedia

    INDEX
    Explanations

    phrases related to introductions and presentations

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

    "introduce" or its variations

    np_acts-logits-general · gemini-2.0-flash

    introducing new things or people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     S
    -0.54
    en
    -0.53
    ar
    -0.51
    boxShadow
    -0.50
     L
    -0.49
     WARN
    -0.49
     out
    -0.49
    na
    -0.49
     G
    -0.48
    FormItem
    -0.47
    POSITIVE LOGITS
     Introduce
    1.35
     introduces
    1.25
    ductory
    1.21
     Introducing
    1.20
     Introdu
    1.20
     introductions
    1.19
    introduce
    1.17
    Introduce
    1.17
     introduce
    1.16
    Introdu
    1.12
    Act Density 0.058%

    No Known Activations