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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and forms of the verb "to be" alongside words related to arts and crafts

    oai_token-act-pair · gemini-2.0-flash

    words indicating actions or processes

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

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imageshack
    -0.58
    
    -0.46
    enumii
    -0.43
     banques
    -0.42
    enumi
    -0.41
     wireType
    -0.41
     giornal
    -0.41
     touristes
    -0.40
    Хьажоргаш
    -0.40
     financières
    -0.40
    POSITIVE LOGITS
    CppMethod
    0.72
    corbic
    0.69
     wanted
    0.69
     removed
    0.68
     pulled
    0.68
     sewed
    0.66
     Utilizamos
    0.66
    AddColumn
    0.66
    脚注の使い方
    0.66
     added
    0.66
    Act Density 0.743%

    No Known Activations