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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate critical or evaluative positions on societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĩ
    -0.18
    etable
    -0.15
    ogle
    -0.15
     авÑĤомаÑĤи
    -0.15
    iad
    -0.15
    mouth
    -0.14
     Verfügung
    -0.14
    ometrics
    -0.14
    otine
    -0.14
    edm
    -0.14
    POSITIVE LOGITS
     campuses
    0.28
     college
    0.24
     farms
    0.23
     beaches
    0.22
     rooft
    0.21
     airplanes
    0.21
     floors
    0.20
     continents
    0.20
     roofs
    0.20
     sidewalks
    0.20
    Act Density 0.107%

    No Known Activations