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

    Neuronpedia

    INDEX
    Explanations

    references to technical details such as model names, specific locations, and codes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Hicks
    -0.95
     Hatt
    -0.85
    ipp
    -0.82
     brace
    -0.80
     bracelet
    -0.75
     Hamas
    -0.75
     ank
    -0.75
    414
    -0.74
    Brook
    -0.74
     Huang
    -0.74
    POSITIVE LOGITS
    V
    1.62
    Vs
    1.45
    VA
    1.42
    v
    1.37
    VD
    1.37
    VC
    1.33
     Vit
    1.33
     V
    1.30
    VG
    1.30
    VP
    1.27
    Act Density 0.535%

    No Known Activations