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

    Neuronpedia

    INDEX
    Explanations

    references to help and assistance

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

    offering or requesting help

    np_acts-logits-general · gemini-2.5-flash-lite

    whether the text is offering or requesting assistance — i.e., expressions of help/assistance.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     setting
    -0.34
     sobres
    -0.32
     mode
    -0.32
    вгения
    -0.31
     kohta
    -0.30
     built
    -0.30
     interface
    -0.30
    IsMutable
    -0.29
     FEES
    -0.29
     certifications
    -0.29
    POSITIVE LOGITS
    help
    1.45
     help
    1.38
    Help
    1.36
     Help
    1.34
    HELP
    1.25
     ayuda
    1.20
     assistance
    1.20
    helping
    1.16
     Assistance
    1.14
     helpers
    1.14
    Act Density 0.069%

    No Known Activations