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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of spatial or contextual proximity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.18
    seite
    -0.15
    aping
    -0.14
    ald
    -0.14
    anna
    -0.14
    skins
    -0.14
    aji
    -0.14
    erek
    -0.14
    holm
    -0.13
    Forge
    -0.13
    POSITIVE LOGITS
    creasing
    0.18
     bounds
    0.18
    within
    0.16
    uze
    0.16
     framework
    0.15
    bounds
    0.15
     Ñģобой
    0.15
    most
    0.15
    ibo
    0.15
    oreach
    0.15
    Act Density 0.038%

    No Known Activations