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

    Neuronpedia

    INDEX
    Explanations

    words related to mysteries, secrets, or enigmas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mystery and unresolved questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ornia
    -0.74
    olt
    -0.69
    attery
    -0.67
    enses
    -0.66
    iere
    -0.66
    baugh
    -0.63
    arna
    -0.63
    erate
    -0.62
    ivals
    -0.62
    ocate
    -0.62
    POSITIVE LOGITS
     solved
    1.38
     unsolved
    1.11
     solving
    1.01
     mystery
    0.98
     surrounding
    0.97
     surrounds
    0.97
     puzzle
    0.96
     puzzles
    0.95
     mysteries
    0.92
     unravel
    0.84
    Act Density 0.060%

    No Known Activations