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

    Neuronpedia

    INDEX
    Explanations

    words related to mysteries

    oai_token-act-pair · gpt-3.5-turbo

    references to mystery or enigmatic situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attery
    -0.89
    baugh
    -0.87
    erate
    -0.79
    onest
    -0.78
    obe
    -0.73
    minster
    -0.72
    boa
    -0.70
    ocate
    -0.70
    tiny
    -0.69
    zer
    -0.67
    POSITIVE LOGITS
     solved
    1.18
     Flavoring
    0.97
     unsolved
    0.96
     surrounds
    0.91
     mystery
    0.88
     mysteries
    0.84
     surrounding
    0.78
     shroud
    0.77
     Mystery
    0.76
     disappearance
    0.73
    Act Density 0.050%

    No Known Activations