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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mysterious or enigmatic topics

    oai_token-act-pair · gpt-3.5-turbo

    references to mysteries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.84
    attery
    -0.84
    obe
    -0.82
    umbnail
    -0.77
    odium
    -0.77
    ocations
    -0.76
    onest
    -0.74
    arf
    -0.73
    ocate
    -0.73
    ornia
    -0.73
    POSITIVE LOGITS
     solved
    0.99
     mysteries
    0.88
     mystery
    0.86
     Flavoring
    0.86
     unsolved
    0.84
     Mystery
    0.84
     surrounds
    0.81
     twist
    0.71
     shroud
    0.70
     puzzles
    0.70
    Act Density 0.024%

    No Known Activations