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

    Neuronpedia

    INDEX
    Explanations

    references to literary works or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATRIX
    -0.17
    cratch
    -0.17
    گرد
    -0.16
    edback
    -0.16
    лÑıд
    -0.15
    _receiver
    -0.15
    oje
    -0.15
    allet
    -0.14
    赫
    -0.14
    odox
    -0.14
    POSITIVE LOGITS
     Drake
    0.33
     trap
    0.30
     Lil
    0.28
     Kendrick
    0.27
    Trap
    0.26
     Trap
    0.25
     Logic
    0.25
     Offset
    0.23
     Chance
    0.23
     rap
    0.23
    Act Density 0.023%

    No Known Activations