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

    Neuronpedia

    INDEX
    Explanations

    instances where certain actions or decisions are being taken in relation to information or data

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data security and its handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ionics
    -0.74
     Raise
    -0.72
     Dice
    -0.72
     Animation
    -0.70
     Tackle
    -0.68
    ciation
    -0.68
    ggle
    -0.65
     Benefits
    -0.64
    tackle
    -0.64
     Cure
    -0.63
    POSITIVE LOGITS
     redacted
    1.26
     anonym
    1.22
     archived
    1.20
     declass
    1.19
     retri
    1.14
     encrypted
    1.13
     forwarded
    1.11
     withheld
    1.10
     transmitted
    1.10
     stored
    1.09
    Act Density 0.194%

    No Known Activations