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

    Neuronpedia

    INDEX
    Explanations

    mentions of something being legendary

    oai_token-act-pair · gpt-3.5-turbo

    the term "legendary" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vere
    -0.79
    getting
    -0.78
    elling
    -0.78
    chn
    -0.77
    arettes
    -0.77
    zos
    -0.75
    chens
    -0.74
    aye
    -0.74
    achment
    -0.74
    ahon
    -0.74
    POSITIVE LOGITS
     Creature
    0.77
     antiquity
    0.76
     legendary
    0.74
     adventurer
    0.74
     tales
    0.73
     treasures
    0.73
     proportions
    0.72
     relics
    0.71
     explorer
    0.71
     beasts
    0.70
    Act Density 0.012%

    No Known Activations