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

    Neuronpedia

    INDEX
    Explanations

    overlooked or forgotten items, people, or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to things that are often disregarded or not given enough attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.75
    rir
    -0.74
    alion
    -0.72
    otaur
    -0.72
    tein
    -0.71
    claimer
    -0.71
    ibal
    -0.70
    obar
    -0.69
    ŃĶ
    -0.68
    ttle
    -0.68
    POSITIVE LOGITS
     Jagu
    0.76
     Sparkle
    0.70
    UF
    0.69
    ãĤĤ
    0.67
     footnote
    0.66
     treasures
    0.66
     Mysteries
    0.65
     amongst
    0.65
     overlooked
    0.63
     nationally
    0.62
    Act Density 0.069%

    No Known Activations