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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpersonal relationships and their dynamics

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

    relationship between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    省市镇
    -0.49
    ftagPool
    -0.45
    posedge
    -0.45
     ✭✭
    -0.45
     astfel
    -0.42
    tidaknya
    -0.41
    harusnya
    -0.40
    fancy
    -0.39
     uș
    -0.39
     fantasía
    -0.39
    POSITIVE LOGITS
     relationship
    1.23
     Relationship
    1.04
    Relationship
    0.94
     RELATIONSHIP
    0.93
    relationship
    0.93
     relation
    0.91
     relationships
    0.89
     relations
    0.77
     Relation
    0.77
     Relationships
    0.77
    Act Density 0.033%

    No Known Activations