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

    Neuronpedia

    INDEX
    Explanations

    phrases related to privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reu
    -0.17
    InView
    -0.15
    iban
    -0.15
    berapa
    -0.15
    kol
    -0.14
    icl
    -0.14
    _principal
    -0.14
    attachments
    -0.14
    mel
    -0.14
    ohana
    -0.14
    POSITIVE LOGITS
    /private
    0.24
     readonly
    0.21
    /public
    0.20
    /Private
    0.19
    ities
    0.17
    izes
    0.17
    ty
    0.17
    -ish
    0.16
    ized
    0.16
    abbrev
    0.16
    Act Density 0.030%

    No Known Activations