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

    Neuronpedia

    INDEX
    Explanations

    indicators of potential spam or problematic edits in a collaborative editing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ECTOR
    -0.15
    Ïĥια
    -0.14
    leÅŁ
    -0.14
    KM
    -0.13
    nech
    -0.13
     min
    -0.13
     meis
    -0.13
     NU
    -0.13
    ieber
    -0.13
    iasm
    -0.12
    POSITIVE LOGITS
    .MixedReality
    0.17
    oad
    0.16
    angelo
    0.16
    ApiClient
    0.15
    inger
    0.15
    ormal
    0.15
    εβ
    0.15
    ael
    0.14
    HTTPRequest
    0.14
    Ñģклад
    0.14
    Act Density 0.014%

    No Known Activations