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

    Neuronpedia

    INDEX
    Explanations

    references to prior research or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     później
    -0.63
     afterward
    -0.62
     later
    -0.61
     senere
    -0.60
     européennes
    -0.60
    bbero
    -0.59
     pozdě
    -0.58
     später
    -0.56
    зулта
    -0.56
     afterwards
    -0.55
    POSITIVE LOGITS
     generations
    1.15
    itisation
    0.99
     iterations
    0.87
     years
    0.85
     incar
    0.84
     eras
    0.80
     decade
    0.79
     generation
    0.78
     year
    0.78
    ImageContext
    0.78
    Act Density 0.151%

    No Known Activations