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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating physical locations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .pub
    -0.16
    itchens
    -0.15
    cheid
    -0.15
    oven
    -0.15
    arb
    -0.14
    stadt
    -0.14
    rieben
    -0.14
    iffe
    -0.14
    ahi
    -0.14
    rab
    -0.14
    POSITIVE LOGITS
     steps
    0.29
     balcony
    0.24
     porch
    0.22
    steps
    0.21
     ver
    0.21
     grass
    0.20
     platform
    0.20
     curb
    0.20
     deck
    0.19
    Steps
    0.19
    Act Density 0.153%

    No Known Activations