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

    Neuronpedia

    INDEX
    Explanations

    terms related to goodwill or positive intentions

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

    goodwill and wishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iksa
    -0.40
    SuppressLint
    -0.38
     them
    -0.35
    マシン
    -0.34
     Parson
    -0.34
    RestController
    -0.34
     Machine
    -0.34
     Utilisez
    -0.34
    身
    -0.33
    Jegyzetek
    -0.33
    POSITIVE LOGITS
     goodwill
    2.02
     Goodwill
    1.93
     friendly
    0.58
     Goodwin
    0.57
     Friendship
    0.56
     friendship
    0.56
     Friendly
    0.56
     Goodrich
    0.55
     friendliness
    0.55
    complexContent
    0.55
    Act Density 0.003%

    No Known Activations