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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

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

    Thanks, thank you, appreciate, related phrases

    np_acts-logits-general · gemini-2.0-flash

    expressions of thanks

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

    expressions of gratitude and appreciation, especially polite thank-you and acknowledgment statements.

    oai_token-act-pair · gpt-5Triggered by @igorkuztech
    New Auto-Interp
    Negative Logits
    BufferException
    -0.86
    oredCriteria
    -0.79
     AssemblyProduct
    -0.76
    setVerticalGroup
    -0.72
     therefore
    -0.72
    withIdentifier
    -0.71
    aarrggbb
    -0.71
    noons
    -0.71
     TestBed
    -0.71
    FormTagHelper
    -0.71
    POSITIVE LOGITS
    おかげ
    0.56
     We
    0.44
    unsqueeze
    0.42
     It
    0.42
     it
    0.41
    readFileSync
    0.41
    We
    0.41
    зе
    0.41
     öns
    0.41
     we
    0.41
    Act Density 0.078%

    No Known Activations