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

    Neuronpedia

    INDEX
    Explanations

    terms related to myths, stories, or famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to legends or legendary figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abus
    -0.80
     Parenthood
    -0.75
    orneys
    -0.74
    artment
    -0.71
    lyak
    -0.70
    pex
    -0.70
    Interstitial
    -0.67
    zers
    -0.67
    ells
    -0.66
    tan
    -0.66
    POSITIVE LOGITS
    arily
    1.13
    lore
    0.85
     tales
    0.85
     legends
    0.85
    Legend
    0.84
    arium
    0.82
     legend
    0.82
    arious
    0.76
     Legend
    0.74
     lore
    0.73
    Act Density 0.016%

    No Known Activations