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

    Neuronpedia

    INDEX
    Explanations

    words related to mystery and the unknown

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mysterious" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     starters
    -0.69
    ariat
    -0.68
    ffen
    -0.65
     Amend
    -0.65
    iew
    -0.62
    istan
    -0.62
     sts
    -0.61
    oway
    -0.60
    opers
    -0.60
     Cycling
    -0.60
    POSITIVE LOGITS
     mysterious
    3.40
     enigmatic
    2.31
     shadowy
    1.89
     Mysterious
    1.89
     cryptic
    1.86
     mystery
    1.84
     unexplained
    1.84
     mysteriously
    1.79
     strange
    1.77
     inexplicable
    1.75
    Act Density 0.020%

    No Known Activations