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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political agreements, negotiations, and conventions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    mistak
    -0.56
     horned
    -0.51
    asserole
    -0.49
     getIndex
    -0.47
    uckoo
    -0.47
    relenting
    -0.47
     frescoes
    -0.47
     Eliot
    -0.47
     horny
    -0.46
     trit
    -0.46
    POSITIVE LOGITS
     package
    1.45
     packages
    1.36
     Package
    1.36
     Packages
    1.27
    Package
    1.24
    package
    1.18
     PACKAGE
    1.11
     pack
    1.08
    packages
    1.07
    PACKAGE
    1.07
    Act Density 0.063%

    No Known Activations