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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "un-" indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.84
     kasarigan
    -0.82
    новниш
    -0.82
     ainfi
    -0.82
     AssemblyCulture
    -0.81
    afficheront
    -0.78
     bluzka
    -0.77
    الحياه
    -0.76
    astéroïdes
    -0.75
     kaarangay
    -0.75
    POSITIVE LOGITS
     arrange
    0.69
     organizing
    0.66
     arranging
    0.64
     organising
    0.60
     Arrange
    0.59
     Organizing
    0.59
     organize
    0.57
     un
    0.57
    Organizing
    0.55
    arrange
    0.54
    Act Density 0.242%

    No Known Activations