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

    Neuronpedia

    INDEX
    Explanations

    phrases comparing quantities or qualities

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

    nothing more than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.69
     plufieurs
    -0.61
     chré
    -0.50
     Verſ
    -0.49
     increí
    -0.49
    tonode
    -0.47
     ſche
    -0.46
     Abonnez
    -0.45
     auffi
    -0.44
     técn
    -0.44
    POSITIVE LOGITS
     merely
    0.62
     مجرد
    0.59
     just
    0.58
     simply
    0.56
     mere
    0.55
     просто
    0.55
    simply
    0.52
     semplicemente
    0.52
    just
    0.52
     lediglich
    0.51
    Act Density 0.011%

    No Known Activations