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

    Neuronpedia

    INDEX
    Explanations

    words related to theft or unauthorized appropriation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or official processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     streng
    -0.75
    paio
    -0.73
     Whe
    -0.73
     lawy
    -0.66
    QUI
    -0.63
     tremend
    -0.60
    Whe
    -0.60
     Briggs
    -0.60
     princ
    -0.59
     COUR
    -0.59
    POSITIVE LOGITS
    ables
    0.94
    ing
    0.93
    ment
    0.92
    able
    0.92
    ership
    0.88
    itures
    0.86
    iture
    0.86
    MENT
    0.83
     receipts
    0.81
    ings
    0.81
    Act Density 0.206%

    No Known Activations