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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horton
    -0.78
     GRATU
    -0.77
     Marston
    -0.71
    Portály
    -0.70
     hoá
    -0.69
     Pears
    -0.67
    hasNext
    -0.67
    Espèce
    -0.65
     Mauritania
    -0.65
    VX
    -0.65
    POSITIVE LOGITS
     Rij
    0.77
     Swin
    0.70
     SAW
    0.70
    ammans
    0.70
     Wils
    0.69
     Archite
    0.68
     Daw
    0.67
    SAW
    0.66
    swt
    0.66
    Iw
    0.66
    Act Density 1.289%

    No Known Activations