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

    Neuronpedia

    INDEX
    Explanations

    words related to locations or places

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    endphp
    -0.85
    日閲覧
    -0.76
     par
    -0.75
     Vos
    -0.73
    Vos
    -0.71
     Keating
    -0.71
    ses
    -0.68
    Leslie
    -0.68
     final
    -0.66
     dem
    -0.66
    POSITIVE LOGITS
     Nowhere
    1.21
     nowhere
    1.19
     Elsewhere
    1.13
    Nowhere
    1.12
    anywhere
    1.09
     Everywhere
    1.08
     purpoſe
    1.07
    Everywhere
    1.05
    everywhere
    1.02
     houſe
    1.01
    Act Density 0.011%

    No Known Activations