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

    Neuronpedia

    INDEX
    Explanations

    mentions of bones or skeletal-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     karet
    -0.57
     puto
    -0.56
     karton
    -0.55
     perak
    -0.54
     lele
    -0.52
     seksi
    -0.51
     Ekonomi
    -0.49
     makro
    -0.49
     sosis
    -0.49
     protokol
    -0.48
    POSITIVE LOGITS
     bone
    1.38
     bones
    1.32
     Bone
    1.25
    Bone
    1.23
    bone
    1.22
     Bones
    1.19
    Bones
    1.17
    bones
    1.16
    BONE
    0.99
     skeleton
    0.88
    Act Density 0.113%

    No Known Activations