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

    Neuronpedia

    INDEX
    Explanations

    references to specific animated television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    817
    -0.07
     Eagles
    -0.06
    hdr
    -0.06
    ForRow
    -0.06
    .borrow
    -0.06
    .twig
    -0.06
    ropa
    -0.06
    alars
    -0.06
    rome
    -0.06
    ursal
    -0.06
    POSITIVE LOGITS
     Springfield
    0.09
     Simpsons
    0.08
     anim
    0.08
     animated
    0.07
    Å¡t
    0.07
     Animation
    0.07
     Homer
    0.07
     animation
    0.07
     Television
    0.07
     television
    0.07
    Act Density 0.030%

    No Known Activations