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

    Neuronpedia

    INDEX
    Explanations

    words related to technology, specifically coding instructions and commands

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    iden
    -0.51
     Gors
    -0.50
    izen
    -0.49
     conflic
    -0.49
     Patriot
    -0.47
    acles
    -0.47
     contag
    -0.46
     metic
    -0.44
    oscope
    -0.43
     vengeance
    -0.43
    POSITIVE LOGITS
    taboola
    0.72
    wcsstore
    0.68
    conv
    0.58
    /-
    0.56
    gypt
    0.53
    âĢİ
    0.53
    lb
    0.52
    AppData
    0.52
    /,
    0.51
    commit
    0.51
    Act Density 7.145%

    No Known Activations