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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to legal documents and procedures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of "privacy" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.75
    lings
    -0.74
    mates
    -0.71
    forth
    -0.70
     filling
    -0.66
    liner
    -0.64
    bound
    -0.63
     Genesis
    -0.62
    going
    -0.61
    nings
    -0.58
    POSITIVE LOGITS
    IME
    1.35
    OPER
    1.34
    OF
    1.32
    INC
    1.31
    ODUCT
    1.28
    ISM
    1.26
    IOR
    1.26
    IZE
    1.23
    INT
    1.19
    ISON
    1.12
    Act Density 0.014%

    No Known Activations