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

    Neuronpedia

    INDEX
    Explanations

    information related to political figures and events as well as legal and investigative processes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Cola
    -1.09
    eker
    -1.05
    ãĥĢ
    -1.05
    elle
    -1.02
    Premium
    -1.01
    Draft
    -0.98
    warming
    -0.98
    spir
    -0.98
    ccording
    -0.97
    !:
    -0.96
    POSITIVE LOGITS
     resume
    0.99
     ease
    0.99
     vice
    0.99
     potentially
    0.92
     GDP
    0.92
     destiny
    0.92
     eliminate
    0.90
     fulfil
    0.88
     its
    0.88
     possibly
    0.88
    Act Density 0.894%

    No Known Activations