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

    Neuronpedia

    INDEX
    Explanations

    the mention of the word "Taylor"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Amm
    -0.76
    Влади
    -0.74
    Amm
    -0.73
     Edmunds
    -0.73
     propOrder
    -0.73
     Hubert
    -0.71
     Stedman
    -0.70
    Edmund
    -0.70
     Vance
    -0.69
     CommonModule
    -0.69
    POSITIVE LOGITS
     Taylor
    1.66
    Taylor
    1.54
     TAYLOR
    1.47
     taylor
    1.41
    AYLOR
    1.41
    taylor
    1.32
     Tay
    1.21
    Tay
    1.14
    aylor
    0.94
    tayl
    0.90
    Act Density 0.001%

    No Known Activations