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

    Neuronpedia

    INDEX
    Explanations

    phrases that quantify and highlight the presence of population statistics, particularly involving halves and thirds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.77
    UpInside
    -0.75
    AutoScaleMode
    -0.74
    estacks
    -0.66
     Augusta
    -0.64
    cektir
    -0.63
    مصادر
    -0.60
    ebilir
    -0.59
     CURIAM
    -0.58
    quiao
    -0.58
    POSITIVE LOGITS
     halfway
    0.91
     Hälfte
    0.90
     half
    0.87
     moitié
    0.85
     mitad
    0.82
     metade
    0.77
     helft
    0.76
     halv
    0.75
    Half
    0.70
    一半
    0.68
    Act Density 0.195%

    No Known Activations