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

    Neuronpedia

    INDEX
    Explanations

    a mix of words related to strong emotions, possibly in a fantasy context

    oai_token-act-pair · gemini-2.0-flash

    multilingual words and phrases

    np_token-act-pair-logits · gpt-4o-mini

    Emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SerializedName
    -0.62
     Roskov
    -0.54
    endphp
    -0.52
    "';
    -0.52
    EndGlobalSection
    -0.51
    nocache
    -0.51
    \"");
    -0.49
    *);
    -0.48
    ()];
    -0.48
    InputTagHelper
    -0.48
    POSITIVE LOGITS
     محفوظة
    0.82
    AndEndTag
    0.66
     peindre
    0.63
    出版年
    0.62
     оригіналу
    0.62
     croire
    0.62
     Grecs
    0.62
     vérit
    0.60
    قایناق‌لار
    0.60
    脚注の使い方
    0.59
    Act Density 2.062%

    No Known Activations