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

    Neuronpedia

    INDEX
    Explanations

    references to fictional locations or worlds

    oai_token-act-pair · gpt-3.5-turbo

    specific fictional location names within fantasy narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     warr
    -0.86
    berman
    -0.72
    bern
    -0.66
    lesi
    -0.61
    hement
    -0.60
    ensible
    -0.60
    rative
    -0.60
     minority
    -0.60
    erate
    -0.60
     SAM
    -0.59
    POSITIVE LOGITS
    opia
    0.87
     Castle
    0.83
    MpServer
    0.83
     Atmosp
    0.79
     Pradesh
    0.79
     Revis
    0.77
     Forever
    0.77
    halla
    0.77
     Reborn
    0.76
     Theme
    0.76
    Act Density 0.115%

    No Known Activations