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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating locations and accommodations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lod
    -0.17
     cabin
    -0.16
     resorts
    -0.16
    adge
    -0.16
    tent
    -0.15
    avn
    -0.15
     cabo
    -0.15
     Cabin
    -0.14
     Empty
    -0.14
    .community
    -0.14
    POSITIVE LOGITS
     Superior
    0.18
     superior
    0.17
    reak
    0.17
     Pension
    0.16
     Conference
    0.16
     rece
    0.16
     conference
    0.16
    eson
    0.16
     modern
    0.16
    ixel
    0.16
    Act Density 0.055%

    No Known Activations