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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographic locations and movements involving people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.87
     الحره
    -0.71
    ]")]
    -0.69
     vectorielles
    -0.61
     modalités
    -0.58
     déclarations
    -0.56
     complètes
    -0.56
     enfans
    -0.55
     histoires
    -0.55
     investissements
    -0.54
    POSITIVE LOGITS
     various
    1.15
     different
    1.04
     places
    0.96
     major
    0.90
    various
    0.90
     schools
    0.88
     cities
    0.87
     areas
    0.86
     certain
    0.84
     communities
    0.84
    Act Density 0.641%

    No Known Activations