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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the act of returning or the origin of something

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

    returning from a destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.62
     الرياضيه
    -0.54
     AssemblyCulture
    -0.53
     ProtoMessage
    -0.53
    Autoritní
    -0.52
    Gön
    -0.50
     مرئيه
    -0.50
    Дереккөздер
    -0.50
    Personendaten
    -0.49
    SourceChecksum
    -0.49
    POSITIVE LOGITS
     abroad
    0.61
     surgery
    0.61
     vacation
    0.61
     trip
    0.60
     overseas
    0.58
     trips
    0.57
     errands
    0.57
     dinner
    0.55
     camping
    0.55
     holidays
    0.53
    Act Density 0.017%

    No Known Activations