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

    Neuronpedia

    INDEX
    Explanations

    references to proximity or location

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ​​
    -0.76
    ionage
    -0.76
    aurus
    -0.75
     يتيمه
    -0.72
    enheim
    -0.72
    \}}
    -0.71
     оригіналу
    -0.69
    ']")
    -0.69
    المشاركات
    -0.66
     Esposito
    -0.66
    POSITIVE LOGITS
    er
    0.88
    erea
    0.81
    ness
    0.79
    NEAR
    0.76
    jshint
    0.76
     NEAR
    0.73
     Args
    0.72
    Cet
    0.72
    anel
    0.71
     neer
    0.70
    Act Density 0.009%

    No Known Activations