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

    Neuronpedia

    INDEX
    Explanations

    phrases inviting participation or collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennie
    -0.15
    pes
    -0.14
    ÑĥÑĢн
    -0.14
    amar
    -0.14
    wy
    -0.13
    lant
    -0.13
    çĬ¶åĨµ
    -0.13
    utting
    -0.13
     kissing
    -0.13
    achment
    -0.13
    POSITIVE LOGITS
     ranks
    0.23
    à¹ĥà¸Ļà¸ģาร
    0.17
    еÑģÑĤва
    0.17
    stdarg
    0.17
     for
    0.16
    ONGL
    0.16
    .scalablytyped
    0.15
    длÑı
    0.15
     dafür
    0.14
     forces
    0.14
    Act Density 0.050%

    No Known Activations