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

    Neuronpedia

    INDEX
    Explanations

    organizational and procedural terms related to political contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     diplom
    -0.69
    lessly
    -0.67
     treating
    -0.66
     hoops
    -0.64
     AFL
    -0.63
     scales
    -0.62
     CPC
    -0.61
    etheless
    -0.61
     realism
    -0.61
     admitting
    -0.61
    POSITIVE LOGITS
    eker
    1.30
    ldom
    1.23
    vere
    1.22
    gments
    1.22
    infeld
    1.12
    asons
    1.11
    vered
    1.10
    greg
    1.09
    xton
    1.09
    verson
    1.09
    Act Density 0.035%

    No Known Activations