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

    thanks to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    -0.45
    /
    -0.40
     and
    -0.38
     Estadual
    -0.36
     would
    -0.34
    ,
    -0.34
     difficult
    -0.33
     not
    -0.33
     State
    -0.33
     should
    -0.32
    POSITIVE LOGITS
    âce
    0.99
    thanks
    0.98
     thanks
    0.96
    Благодаря
    0.96
     благодаря
    0.94
     THANKS
    0.94
    ValueStyle
    0.92
     graças
    0.89
    gracias
    0.89
     grâce
    0.89
    Act Density 0.009%

    No Known Activations