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

    Neuronpedia

    INDEX
    Explanations

    terms related to models or replicas of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥ§ãĥ³
    -0.14
    æĿ
    -0.14
    msgid
    -0.14
    CCC
    -0.14
    _quest
    -0.13
    ouses
    -0.13
    athom
    -0.13
     cushion
    -0.13
    usiness
    -0.13
     Shepard
    -0.13
    POSITIVE LOGITS
     Hobby
    0.24
     hobby
    0.21
     scale
    0.20
     Scale
    0.19
     kit
    0.19
    kit
    0.18
     models
    0.18
    模åŀĭ
    0.18
    aler
    0.18
    scale
    0.17
    Act Density 0.009%

    No Known Activations