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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating urgency or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irim
    -0.16
    ells
    -0.15
    ernes
    -0.15
     Ludwig
    -0.15
    ersen
    -0.15
    undo
    -0.15
     Walton
    -0.15
     crust
    -0.15
    yps
    -0.15
    794
    -0.14
    POSITIVE LOGITS
    ingles
    0.18
     wash
    0.16
    ách
    0.15
    еÑģи
    0.15
    inski
    0.15
     sink
    0.15
    avr
    0.15
    Sink
    0.15
     Sink
    0.14
    iad
    0.14
    Act Density 0.031%

    No Known Activations