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

    Neuronpedia

    INDEX
    Explanations

    terms related to mysterious or enigmatic elements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mysterious."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.78
    mys
    -0.77
    hers
    -0.75
    brance
    -0.74
    berman
    -0.74
    neys
    -0.73
    arf
    -0.73
    SN
    -0.73
    heit
    -0.73
    Supported
    -0.72
    POSITIVE LOGITS
     occurrences
    0.96
     mysterious
    0.96
     circumstances
    0.87
     coincidence
    0.86
    worldly
    0.84
     substances
    0.82
     unexplained
    0.81
     anomalies
    0.80
     purple
    0.79
     creatures
    0.78
    Act Density 0.056%

    No Known Activations