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

    Neuronpedia

    INDEX
    Explanations

    terms associated with abuse and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rei
    -0.17
    iky
    -0.17
    atura
    -0.15
    istributions
    -0.15
    ness
    -0.15
    lify
    -0.15
    ãĤ·ãĤ¢
    -0.15
    omb
    -0.15
    wy
    -0.14
    gorithm
    -0.14
    POSITIVE LOGITS
    erland
    0.18
    fully
    0.18
    /add
    0.16
    ortion
    0.16
     Dhabi
    0.16
    ãĥ¥
    0.16
    uos
    0.15
     dụng
    0.15
    uous
    0.15
    antly
    0.15
    Act Density 0.008%

    No Known Activations