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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "into" indicating transitions or changes in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    duration and sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     culturelles
    -0.31
     yüzde
    -0.28
     aéreo
    -0.26
    <bos>
    -0.26
     sexuales
    -0.26
     financières
    -0.26
    exc
    -0.23
     fallait
    -0.23
     händer
    -0.22
    亲
    -0.22
    POSITIVE LOGITS
    zzleHttp
    0.78
    sidemargin
    0.77
     fashiola
    0.72
     ſua
    0.70
     resourceCulture
    0.70
    ஋
    0.70
     linkovi
    0.69
     témoig
    0.69
     Monfieur
    0.69
     GenerationType
    0.69
    Act Density 0.009%

    No Known Activations