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

    Neuronpedia

    INDEX
    Explanations

    locations or geographical regions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote specific geographical regions or areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maid
    -0.81
    etheus
    -0.68
    /+
    -0.68
     recomm
    -0.68
    \\\\\\\\
    -0.65
    lda
    -0.65
     bless
    -0.64
    SAY
    -0.64
     sqor
    -0.63
     Picks
    -0.63
    POSITIVE LOGITS
     periphery
    0.98
     contiguous
    0.81
    outheast
    0.79
     adjoining
    0.77
     boundary
    0.75
     southeastern
    0.75
     locality
    0.74
     Northeast
    0.74
     northeastern
    0.74
     radius
    0.73
    Act Density 0.225%

    No Known Activations