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

    Neuronpedia

    INDEX
    Explanations

    terms related to confidentiality and legal obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neglected
    -0.15
    514
    -0.14
    á»ħ
    -0.13
    inic
    -0.13
    endants
    -0.13
    ÙĪرد
    -0.13
    èo
    -0.13
    身ä¸Ĭ
    -0.13
    _VALID
    -0.13
    os
    -0.13
    POSITIVE LOGITS
     confidential
    0.48
     confidentiality
    0.47
     privacy
    0.45
     Confidential
    0.44
     anonymity
    0.39
    privacy
    0.39
     conf
    0.38
     anonymous
    0.38
     Privacy
    0.38
    Privacy
    0.37
    Act Density 0.144%

    No Known Activations