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

    Neuronpedia

    INDEX
    Explanations

    occurrences of prepositions indicating location or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stroy
    -0.15
     Streaming
    -0.14
    elyn
    -0.14
    絡
    -0.13
    ptal
    -0.13
    .scalablytyped
    -0.13
    throat
    -0.13
    ltra
    -0.13
    itez
    -0.13
    /Dk
    -0.13
    POSITIVE LOGITS
     stil
    0.24
     horse
    0.22
     route
    0.21
     approach
    0.21
     impulse
    0.20
     pilgrimage
    0.20
     foot
    0.19
     Route
    0.19
     arriving
    0.19
     arrival
    0.19
    Act Density 0.140%

    No Known Activations