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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     psicológica
    -0.36
     betre
    -0.35
     decorativo
    -0.35
    sold
    -0.33
    exact
    -0.32
     Wicidata
    -0.32
     утвер
    -0.32
     виру
    -0.31
    ตะ
    -0.31
     CreateTagHelper
    -0.31
    POSITIVE LOGITS
     courteous
    0.75
     politeness
    0.69
    ArgsConstructor
    0.68
     thanked
    0.68
     polite
    0.67
     thanking
    0.67
     courtesy
    0.65
     THANK
    0.65
    grazie
    0.64
     tan
    0.63
    Act Density 1.681%

    No Known Activations