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

    Neuronpedia

    INDEX
    Explanations

    numeric values, particularly those related to dates or sequence identifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.91
    AndEndTag
    -0.89
     ModelRenderer
    -0.82
     Monfieur
    -0.82
    #+#
    -0.81
     通販
    -0.80
    ########.
    -0.79
    paravant
    -0.77
    hability
    -0.77
     betweenstory
    -0.77
    POSITIVE LOGITS
     future
    0.55
     
    0.51
    future
    0.48
     no
    0.45
    <eos>
    0.44
     prz
    0.43
    Auto
    0.43
    </h2>
    0.43
     NO
    0.41
    
    0.41
    Act Density 0.031%

    No Known Activations