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

    Neuronpedia

    INDEX
    Explanations

    sentences that express regret or seek retraction

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

    Follows quotation marks or dialogue opening

    np_acts-logits-general · gemini-2.0-flash

    offer/request to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    -0.84
     (&
    -0.78
     &
    -0.77
    )&
    -0.68
     ("
    -0.66
     ujednoznacz
    -0.66
    
    -0.65
     ("%
    -0.64
     "/
    -0.63
     "#
    -0.63
    POSITIVE LOGITS
    —”
    1.90
    -”
    1.66
    —"
    1.52
    …”
    1.47
    ——”
    1.45
    -“
    1.34
    -"
    1.32
    —“
    1.31
    --"
    1.31
    ...”
    1.31
    Act Density 0.296%

    No Known Activations