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

    Neuronpedia

    INDEX
    Explanations

    references to close physical distances or relationships in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of physical closeness or nearness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    err
    -0.84
    YR
    -0.79
    sb
    -0.73
    inn
    -0.72
    tailed
    -0.71
    girls
    -0.70
    udeb
    -0.70
    ocker
    -0.69
    Merit
    -0.69
    OY
    -0.69
    POSITIVE LOGITS
     proximity
    1.23
     thereto
    0.85
     minded
    0.70
     prox
    0.69
    imity
    0.69
     charms
    0.68
     vicinity
    0.67
     Ascend
    0.67
    itiz
    0.66
     neighbours
    0.66
    Act Density 0.019%

    No Known Activations