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

    Neuronpedia

    INDEX
    Explanations

    references to underground structures and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jadx
    -0.15
    het
    -0.15
    вÑģÑı
    -0.15
    мом
    -0.14
    å»Ĭ
    -0.14
    attered
    -0.14
     caster
    -0.14
     tái
    -0.14
    emale
    -0.13
    awner
    -0.13
    POSITIVE LOGITS
     beneath
    0.24
     depths
    0.21
     depth
    0.21
     deepest
    0.21
     bur
    0.20
     underneath
    0.18
     deep
    0.18
     deeper
    0.18
    depth
    0.18
     Depth
    0.18
    Act Density 0.379%

    No Known Activations