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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the purpose or intent behind actions or studies

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

    "purpose"

    np_acts-logits-general · gemini-2.0-flash

    purpose of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.82
     HasFactory
    -0.76
    ")));
    -0.74
    Jeografia
    -0.72
     חיצוניים
    -0.71
    istoitu
    -0.65
    '},
    -0.65
    "},
    -0.64
    InputBorder
    -0.61
     GoogleFonts
    -0.58
    POSITIVE LOGITS
     purposes
    1.11
    fulness
    0.96
     Purpose
    0.94
     Purposes
    0.94
     purpose
    0.93
    Purpose
    0.90
    purposes
    0.87
     PURPOSE
    0.86
     propósitos
    0.81
    PURPOSE
    0.77
    Act Density 0.096%

    No Known Activations