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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "home."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.65
    titas
    -0.53
    égard
    -0.52
     tryck
    -0.52
    setLine
    -0.52
    rechter
    -0.51
     versucht
    -0.50
    üedad
    -0.50
     vært
    -0.50
    iela
    -0.50
    POSITIVE LOGITS
     pulang
    0.92
     home
    0.88
     repatri
    0.81
     homecoming
    0.80
     домой
    0.79
     homeward
    0.75
    回家
    0.71
    tagHelperRunner
    0.66
     hjem
    0.65
     repatriation
    0.65
    Act Density 0.103%

    No Known Activations