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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.50
    Microkernel
    -0.40
     怎样
    -0.40
    ůli
    -0.40
    wijl
    -0.39
     peggio
    -0.39
    worst
    -0.38
    льності
    -0.37
     pihaknya
    -0.36
    ród
    -0.36
    POSITIVE LOGITS
     very
    0.90
    very
    0.65
     again
    0.59
    GOTREF
    0.59
    MemoryWarning
    0.59
     kindly
    0.58
    Very
    0.57
     muito
    0.57
     VERY
    0.55
    Muito
    0.55
    Act Density 0.053%

    No Known Activations