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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unconfirmed
    -0.65
     defaultstate
    -0.65
    setVerticalGroup
    -0.58
     Signalez
    -0.54
    '))
    -0.53
     informée
    -0.50
    initComponents
    -0.50
    princip
    -0.49
     autorytatywna
    -0.49
    /}.
    -0.48
    POSITIVE LOGITS
     universel
    0.77
     universal
    0.75
    Universal
    0.73
     uniwers
    0.73
    universal
    0.69
     universale
    0.68
    UNIVERS
    0.68
     Universal
    0.68
     univerz
    0.66
     UNIVERSAL
    0.64
    Act Density 0.179%

    No Known Activations