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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographic concentrations and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.06
    4:0.14
    5:0.03
    6:0.04
    7:0.39
    8:0.03
    9:0.03
    10:0.08
    11:0.05
    Negative Logits
     condem
    -1.73
    obyl
    -1.42
     {*
    -1.41
     sugg
    -1.39
     inquire
    -1.37
     bye
    -1.36
     caller
    -1.35
    informed
    -1.34
     opener
    -1.33
     inquired
    -1.30
    POSITIVE LOGITS
    population
    1.71
    ocated
    1.61
     distributing
    1.46
     concentration
    1.43
    ocating
    1.43
     scattering
    1.41
    ooth
    1.39
     translating
    1.37
     clearing
    1.36
    tical
    1.36
    Act Density 0.003%

    No Known Activations