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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or confirmations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Sao
    -0.69
     Los
    -0.63
     Thomas
    -0.63
     Blair
    -0.62
    antz
    -0.59
    "");
    -0.59
     sao
    -0.59
     tract
    -0.57
    Franz
    -0.57
     Tribune
    -0.57
    POSITIVE LOGITS
     YES
    1.16
    YES
    1.10
     Yes
    1.00
    yes
    0.99
    Yes
    0.96
     Noyes
    0.93
    ISupport
    0.90
     NSCoder
    0.88
     препратки
    0.87
     yes
    0.86
    Act Density 0.065%

    No Known Activations