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

    Neuronpedia

    INDEX
    Explanations

    preferences and activities related to personal interests and hobbies

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

    things people like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    invokeLater
    -0.69
     NSCoder
    -0.68
    UnsafeEnabled
    -0.65
    pecabe
    -0.65
     createSlice
    -0.65
    #
    -0.64
    \{\\
    -0.63
    +:+
    -0.63
     Geiſt
    -0.62
    SourceChecksum
    -0.62
    POSITIVE LOGITS
     and
    0.35
     especially
    0.26
     likes
    0.25
     peuple
    0.23
     particularly
    0.23
     liking
    0.23
     gond
    0.23
     AssemblyCompany
    0.23
     policial
    0.23
     dan
    0.23
    Act Density 0.006%

    No Known Activations