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

    Neuronpedia

    INDEX
    Explanations

    shortened or alternative versions of entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "version" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usters
    -0.97
    veyard
    -0.75
     charism
    -0.73
    inently
    -0.69
    ulhu
    -0.68
    ãĤī
    -0.68
    iencies
    -0.66
     Rings
    -0.66
    friends
    -0.65
    uster
    -0.64
    POSITIVE LOGITS
     thereof
    1.11
     version
    1.00
     versions
    0.94
    UID
    0.83
    Versions
    0.83
    lihood
    0.82
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.68
     VERS
    0.66
    CRIP
    0.66
    tera
    0.65
    Act Density 0.026%

    No Known Activations