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

    Neuronpedia

    INDEX
    Explanations

    segments of code or numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )");
    -0.95
    />";
    -0.85
    fromnode
    -0.84
     ivelany
    -0.82
    )"),
    -0.81
     saites
    -0.80
    você
    -0.80
    — 
    -0.78
     />";
    -0.77
    Географиясе
    -0.77
    POSITIVE LOGITS
    0
    0.87
    mitives
    0.66
     Ersten
    0.63
     absoluto
    0.61
     Zer
    0.58
     Nan
    0.57
    ZERO
    0.56
     Zero
    0.56
    anceled
    0.55
    َي
    0.55
    Act Density 0.421%

    No Known Activations