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

    Neuronpedia

    INDEX
    Explanations

    references to novel approaches or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mani
    -0.54
     sensi
    -0.53
     procur
    -0.52
     Barnabas
    -0.50
     sot
    -0.50
     abf
    -0.50
     Montaigne
    -0.50
     multip
    -0.49
     blan
    -0.49
     nir
    -0.49
    POSITIVE LOGITS
     surla
    0.79
     novedades
    0.76
    tvguidetime
    0.67
     burbujas
    0.67
     tradição
    0.66
     generaciones
    0.65
     ExecuteAsync
    0.65
     novedad
    0.64
    AutoScaleMode
    0.63
    colgante
    0.63
    Act Density 0.196%

    No Known Activations