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

    Neuronpedia

    INDEX
    Explanations

    phrases that express gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -1.04
    rungsseite
    -0.92
    OGND
    -0.87
     Normdatei
    -0.82
    enterOuterAlt
    -0.81
    WriteLiteral
    -0.79
    sidemargin
    -0.78
    InputBorder
    -0.78
    NameInMap
    -0.78
    adpleegd
    -0.77
    POSITIVE LOGITS
     welcome
    0.60
     your
    0.59
     appreciated
    0.57
     appreciate
    0.57
     appreci
    0.57
     shared
    0.56
     Appreciate
    0.55
     vectoriales
    0.54
     thank
    0.54
    Appreciate
    0.53
    Act Density 0.046%

    No Known Activations