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

    Neuronpedia

    INDEX
    Explanations

    references to influence, choice, or decision-making dynamics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.74
     resourceCulture
    -0.74
     pinulongan
    -0.73
    -0.70
     himo
    -0.67
    utilisons
    -0.66
    writeFieldEnd
    -0.65
    ContentAsync
    -0.65
     ExecuteAsync
    -0.64
    rawDesc
    -0.64
    POSITIVE LOGITS
     to
    0.52
    ในการ
    0.51
     untuk
    0.46
     regarding
    0.44
     Regarding
    0.43
     để
    0.41
    Regarding
    0.40
    udessa
    0.40
    armament
    0.40
     جهت
    0.40
    Act Density 0.549%

    No Known Activations