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

    Neuronpedia

    INDEX
    Explanations

    single letters, mainly "a", used for enumerations or lists

    oai_token-act-pair · gemini-2.0-flash

    token 'a' and related context

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

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.55
     e
    -0.55
    utas
    -0.48
    za
    -0.48
     Gran
    -0.48
    issa
    -0.47
     gran
    -0.47
    ora
    -0.46
    lan
    -0.46
    or
    -0.46
    POSITIVE LOGITS
     مشين
    0.95
     الرياضيه
    0.94
    脚注の使い方
    0.93
    expandindo
    0.91
     createSlice
    0.90
    +#+#
    0.86
    RenderAtEndOf
    0.83
     فريبيس
    0.81
     المعيارى
    0.81
    IntoConstraints
    0.80
    Act Density 0.852%

    No Known Activations