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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating proximity or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.75
     Erfurt
    -0.73
     purpoſe
    -0.69
     Anſ
    -0.67
     Diſ
    -0.65
     Houſe
    -0.60
     Cæsar
    -0.59
    <bos>
    -0.59
     SqlDbType
    -0.58
    phosa
    -0.58
    POSITIVE LOGITS
     near
    1.08
     Near
    1.01
    near
    0.98
    Near
    0.97
     возле
    0.92
     beside
    0.88
     NEAR
    0.87
     près
    0.82
    NEAR
    0.81
     dekat
    0.79
    Act Density 0.176%

    No Known Activations