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

    Neuronpedia

    INDEX
    Explanations

    references to specific animated television series and their related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ova
    -0.15
    umas
    -0.15
    erez
    -0.15
    908
    -0.15
     overhead
    -0.14
    ippy
    -0.14
    808
    -0.14
    lg
    -0.14
    817
    -0.14
    ãģ¨ãģĵãĤį
    -0.14
    POSITIVE LOGITS
     Simpsons
    0.32
     Simpson
    0.31
     Springfield
    0.30
     Homer
    0.28
    simp
    0.26
     Bart
    0.24
     simp
    0.21
     Couch
    0.21
    (simp
    0.20
     couch
    0.19
    Act Density 0.043%

    No Known Activations