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

    Neuronpedia

    INDEX
    Explanations

    concepts related to humor, particularly black humor, and its association with education and socioeconomic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingt
    -0.17
     Demp
    -0.15
    ÃŃnh
    -0.15
     NSA
    -0.14
    antine
    -0.14
    -0.14
     transporter
    -0.14
     desn
    -0.13
    ULAR
    -0.13
     simp
    -0.13
    POSITIVE LOGITS
     repression
    0.30
     unconscious
    0.24
     Freud
    0.20
     displaced
    0.20
     edip
    0.20
     Projection
    0.20
     complexes
    0.20
     latency
    0.20
     defensive
    0.20
     projection
    0.19
    Act Density 0.029%

    No Known Activations