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

    Neuronpedia

    INDEX
    Explanations

    physical actions and descriptions involving body parts, physical feelings, and locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lance
    -1.03
     guiActiveUn
    -0.98
    ONSORED
    -0.94
    aurus
    -0.90
    stats
    -0.87
    atz
    -0.87
     Calls
    -0.86
    6666
    -0.86
     specialization
    -0.85
     boycot
    -0.82
    POSITIVE LOGITS
     gently
    1.07
    stretched
    1.02
     damp
    1.01
     lightly
    1.00
     icy
    0.98
     shoulder
    0.98
     sandy
    0.96
     wet
    0.96
     securely
    0.94
     tightly
    0.94
    Act Density 0.859%

    No Known Activations