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

    Neuronpedia

    INDEX
    Explanations

    expressions of persuasion and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fhir
    -0.67
    MessageTagHelper
    -0.65
    tz
    -0.63
    nbsp
    -0.60
    息
    -0.59
    gameserver
    -0.57
     mulighed
    -0.56
     AUSSI
    -0.55
     Sal
    -0.55
    尽
    -0.55
    POSITIVE LOGITS
     persuaded
    1.77
     convinced
    1.71
     persuading
    1.65
     convince
    1.64
     persuade
    1.63
     convincing
    1.61
     convinces
    1.61
     persu
    1.58
     persuasion
    1.54
     convencer
    1.45
    Act Density 0.132%

    No Known Activations