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

    Neuronpedia

    INDEX
    Explanations

    percentage values in texts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    raltar
    -1.10
    achus
    -1.10
    ModLoader
    -1.08
    raints
    -0.99
    rament
    -0.98
    necess
    -0.98
    necessary
    -0.98
    accompan
    -0.98
    omnia
    -0.96
    adobe
    -0.91
    POSITIVE LOGITS
    3333
    0.92
    rc
    0.85
    BSD
    0.84
     WRITE
    0.81
    GHz
    0.80
     GHz
    0.80
     WAR
    0.78
     ERA
    0.77
    6666
    0.77
    ACE
    0.77
    Act Density 0.631%

    No Known Activations