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

    Neuronpedia

    INDEX
    Explanations

    words that express agreement or connection between ideas in a discussion or argument

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    urante
    -0.64
    oxys
    -0.63
     theo
    -0.59
    ArrowToggle
    -0.59
     configureStore
    -0.58
    Rüyada
    -0.56
     Denn
    -0.55
    YON
    -0.55
    shmi
    -0.55
     TableColumn
    -0.54
    POSITIVE LOGITS
     bahwa
    0.71
     Normdatei
    0.66
    stateProvider
    0.62
     that
    0.60
     חיצוניים
    0.59
     iemand
    0.57
     lèvres
    0.55
    󠁴
    0.53
     oreilles
    0.52
     inwardly
    0.52
    Act Density 0.167%

    No Known Activations