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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and helpfulness

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

    Expression of hope or help

    np_acts-logits-general · gemini-2.0-flash

    hope that helps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.73
    TagMode
    -0.67
    TemporalType
    -0.65
     TType
    -0.64
    Datuak
    -0.64
    awtextra
    -0.64
    SequentialGroup
    -0.63
    Geplaatst
    -0.62
    PMailer
    -0.60
    AddTagHelper
    -0.59
    POSITIVE LOGITS
     „
    0.28
    „
    0.28
    Sea
    0.27
     consideración
    0.26
     jums
    0.26
     enjoyment
    0.25
    info
    0.25
    NF
    0.25
     cassa
    0.24
     interest
    0.24
    Act Density 0.143%

    No Known Activations