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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to social interactions and greetings, particularly handshakes

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

    handshakes hugs and kisses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Evaluator
    -0.37
     Cat
    -0.36
    院
    -0.35
     Live
    -0.35
     Living
    -0.35
    Exponent
    -0.35
    FetchType
    -0.35
     vertre
    -0.35
    getActivity
    -0.34
    PONENT
    -0.34
    POSITIVE LOGITS
    AndEndTag
    0.75
     handshake
    0.69
     الحره
    0.68
     незавершена
    0.67
    WriteBarrier
    0.66
    Personendaten
    0.66
     hugs
    0.65
     kisses
    0.61
     ProtoMessage
    0.59
     hug
    0.59
    Act Density 0.023%

    No Known Activations