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

    Neuronpedia

    INDEX
    Explanations

    commands or prompts related to selection and choice

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

    choose or select

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    filesize
    -0.48
    showConfirm
    -0.45
    ież
    -0.45
     reality
    -0.45
     niya
    -0.44
     footnote
    -0.42
    全文
    -0.41
     odkazy
    -0.41
    reality
    -0.41
     plancher
    -0.41
    POSITIVE LOGITS
    Choose
    1.16
     Choose
    1.10
     choosing
    1.00
     choose
    1.00
     Choosing
    0.99
    choose
    0.98
    Choosing
    0.95
     chosen
    0.94
    Pick
    0.93
     selecting
    0.93
    Act Density 0.031%

    No Known Activations