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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their relationships in data contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.68
     سكانية
    -0.66
    ])))
    -0.59
    ']):
    -0.57
    )}>
    -0.57
    ParallelGroup
    -0.56
     références
    -0.56
    <eos>
    -0.55
    ++];
    -0.55
     '\\;'
    -0.54
    POSITIVE LOGITS
     تضيفلها
    0.63
    borderSide
    0.52
    SourceChecksum
    0.52
    djangoproject
    0.51
    OOTDTY
    0.50
     propOrder
    0.49
    ifrance
    0.49
     ModelRenderer
    0.49
    composición
    0.48
     useParams
    0.48
    Act Density 0.028%

    No Known Activations