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

    Neuronpedia

    INDEX
    Explanations

    references to spatial relationships and proximity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.47
     \
    -0.42
     uitges
    -0.40
     deney
    -0.36
     }^{\
    -0.36
     tjen
    -0.35
    achelor
    -0.33
     Denial
    -0.33
     faculty
    -0.32
    Dea
    -0.32
    POSITIVE LOGITS
    Around
    1.45
    around
    1.45
     AROUND
    1.44
     around
    1.39
     Around
    1.38
    AROUND
    1.28
     autour
    1.06
     вокруг
    1.05
     alrededor
    0.99
     okolo
    0.98
    Act Density 0.091%

    No Known Activations