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

    Neuronpedia

    INDEX
    Explanations

    positive attributes and expressions of appreciation

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

    Salutations (Mr, sir, dear)

    np_acts-logits-general · gemini-2.0-flash

    terms of address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.72
    numerusform
    -0.66
    TagHelpers
    -0.63
    casila
    -0.61
    참고
    -0.61
     Yugoslav
    -0.60
    SBATCH
    -0.60
    rzez
    -0.59
     mukana
    -0.58
     فريبيس
    -0.58
    POSITIVE LOGITS
     Mr
    1.03
     sir
    1.01
    Mr
    0.85
     guys
    0.83
     dear
    0.81
     señor
    0.79
     Sir
    0.77
     mate
    0.77
     dude
    0.75
     brother
    0.72
    Act Density 0.207%

    No Known Activations