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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating social interactions and relationships

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

    purpose of action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    processed
    -0.33
    高质量
    -0.32
     contacter
    -0.32
    点了点头
    -0.32
     kuid
    -0.32
    Попис
    -0.31
     Kontakte
    -0.30
     Organizador
    -0.30
     contacts
    -0.30
     processed
    -0.29
    POSITIVE LOGITS
     linkovi
    0.54
     ModelExpression
    0.53
     Numerade
    0.51
     Италијани
    0.50
    PyExc
    0.50
     &___
    0.48
    windowFixed
    0.48
    ⏪
    0.47
    saraba
    0.46
    onghi
    0.46
    Act Density 0.059%

    No Known Activations