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

    Neuronpedia

    INDEX
    Explanations

    terms related to personal relationships and social dynamics

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

    Follows nouns referring to people

    np_acts-logits-general · gemini-2.0-flash

    noun followed by who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     containing
    -0.49
     Relating
    -0.48
     relevant
    -0.47
    being
    -0.46
     featuring
    -0.46
     relating
    -0.45
     involving
    -0.43
    for
    -0.42
    containing
    -0.41
     correspondant
    -0.41
    POSITIVE LOGITS
     who
    1.09
    BeginContext
    1.04
     whoſe
    0.96
     estekak
    0.93
    ########.
    0.91
    findpost
    0.91
    UnusedPrivate
    0.89
    tvguidetime
    0.89
     whofe
    0.86
     Савезне
    0.86
    Act Density 0.380%

    No Known Activations