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

    Neuronpedia

    INDEX
    Explanations

    locations or places within descriptions

    oai_token-act-pair · gpt-3.5-turbo

    locations and surfaces in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩ
    -0.74
    thood
    -0.67
    CHQ
    -0.65
     href
    -0.65
     Matters
    -0.64
    ongyang
    -0.64
     Emails
    -0.62
    olitics
    -0.62
    ilon
    -0.60
    audi
    -0.58
    POSITIVE LOGITS
     beside
    1.12
     below
    0.96
     outside
    0.94
     floor
    0.93
     beneath
    0.91
    side
    0.87
     ledge
    0.86
    walk
    0.85
     opposite
    0.85
     periphery
    0.85
    Act Density 0.144%

    No Known Activations