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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical implants and their associated risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jets
    -0.17
     Hayden
    -0.16
     jet
    -0.15
    BlockSize
    -0.14
    okia
    -0.14
     whe
    -0.14
    masked
    -0.14
    AMB
    -0.14
     Bob
    -0.14
     electricity
    -0.14
    POSITIVE LOGITS
     implant
    0.42
     implants
    0.42
    impl
    0.36
     implanted
    0.35
    Impl
    0.31
    _impl
    0.29
     Impl
    0.28
    _Impl
    0.28
     titanium
    0.26
     Titanium
    0.24
    Act Density 0.030%

    No Known Activations